Skip to main content
Chemia Discovery
Browse the documentation

show_eliminated tool

Shows the candidates an earlier search eliminated, closest miss first, so you can see how near each one came to passing. It is not charged against the daily allowance.

At a glance
Toolshow_eliminated
TitleShow eliminated candidates
GroupWork with a result set
ChargedNo
Read-onlyYes
Parameters3, of which 1 required

What parameters does show_eliminated take?

Parameters of show_eliminated
ParameterTypeRequiredDefaultWhat it does
set_idstringYesnoneThe result_set_id of an earlier search, or of a set derived from one. Only result sets created by your own account are readable.
constraintstring or nullNonot setKeeps only eliminations whose constraint name or stage contains this text, ignoring case: "thermal" matches "thermal_conductivity". Null (the default) shows every eliminated candidate.
limitintegerNo20How many candidates to return, capped at 50. There is no offset: use a narrower constraint to reach others.

Does show_eliminated use my daily allowance?

  • Charged: no, it never uses the daily allowance.
  • Who can call it: your client lists the tools your account is entitled to, so a tool appears only when you can use it.

The allowance and the account rules are explained in Access and limits.

Annotations the server sets on show_eliminated
AnnotationValueMeaning
idempotentHinttrueIf true, calling the tool again with the same arguments has no additional effect.
openWorldHintfalseIf true, the tool may interact with an open world of external entities.
readOnlyHinttrueIf true, the tool does not modify its environment.

What does a call to show_eliminated look like?

The ten closest misses on one constraint.

Example arguments for show_eliminated
{
  "set_id": "3f2b8e9a-0c1d-4e7f-9a6b-5d4c3b2a1f00",
  "constraint": "band_gap",
  "limit": 10
}

These arguments show how a call is written and validate against the tool's input schema.

How should I read show_eliminated results?

  • Good to know. total is how many materials were eliminated; stored is how many the set kept to show, which for a search is the closest 50 per constraint. total, not stored, answers "how many failed".
  • Good to know. Candidates are sorted by violation_amount, the shortfall in the property's unit to four significant figures. A candidate removed for lacking a value has no violation amount and is listed after every measured near miss.

"Good to know" explains a field whose meaning is not obvious, "Check this" marks a result that can look right and still mislead, and "Coverage note" says what the data does not cover. Reading results explains all three.

How does the server describe show_eliminated?

This is the description an assistant sees for the tool.

List candidates an earlier search eliminated from set_id, sorted by violation_amount ascending (closest miss first), "how close did the near-misses come", not the survivors search_materials/ get_result_set already return.

constraint filters to eliminations matching that name or stage (substring, case-insensitive), e.g. "thermal" matches "thermal_conductivity". Omit it to see every eliminated candidate.

total is how many materials were eliminated (on that constraint, or on all): the search's own ledger count, plus every elimination a refine_result_set made. stored is how many of them the result set kept to show (the search keeps its closest 50 per constraint), and limit (max 50) is how many come back; there is no offset, so a narrower constraint reaches others. total, not stored, is "how many failed". Each candidate carries its chemia_id (the id users see; material_id is internal), violation_amount to four significant figures, and the property's unit.

limit is capped at 50 regardless of what's asked for, the same context-budget ceiling as this server's other tools; check limit_applied/notice rather than assuming the count matches what was asked for. Only a result set this account owns AND is still entitled to the source of can be read here, same rule as get_result_set.

show_eliminated is in the group "Work with a result set". The other tools in it:

  • benchmark_against: Compares the top five of a scored result set with a named incumbent material across the properties the set was scored on.
  • export_result_set: Prepares a CSV or JSON file of an earlier result set's full stored match list and returns a download link and a resource to read it from.
  • get_result_set: Pages through the stored matches of an earlier search, up to 50 rows at a time, with the match totals and a next_offset to continue from.
  • plot_results: Returns the data behind a chart of an earlier result set (bar, spider or Ashby) for you to draw or describe.
  • refine_result_set: Narrows an earlier search's stored matches with extra property limits or element filters, without re-running the search. Returns a new result set; the original is unchanged.
  • rerank_result_set: Re-orders an earlier result set, either by one property or by a new weighting of its constraints, and returns a new result set.
  • score_results: Ranks an earlier search's stored matches by a weighted score across its constraints and returns a new result set whose rows are in ranked order.

The Tool reference lists every tool.