Skip to main content
Glama

find_facts

Retrieve facts saved from datasheet documents by part number, document, or text query, including base-part facts, then check important values against the original source.

Instructions

Find values that were read before (save_fact). With part, it searches the documents of the part and of its base part: a concrete MPN also finds the facts of its datasheet. Gives one line for each fact: number, subject, value, the part (when the fact is for one part of a document of more parts), column, conditions, source (document, page, element or region), state and author. A fact is not the source of truth: check an important value against the original, then set its state with set_fact_status.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_facts"
  }
}

Input Schema

NameRequiredDescriptionDefault
partNoA part number (MPN) or an alias. Case is ignored.
limitNoThe maximum number of facts (1 to 500).
queryNoA text in the subject or the value. Empty: all facts.
documentNoThe document: its reference from list_documents, project_status or add_document (the first 12 characters of its SHA-256). A longer SHA-256 prefix or the numeric document ID also works.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the load and does well: it discloses the base-part/datasheet widening of the search scope, the per-fact line format including source provenance (document, page, element/region) and author, and the important caveat that a fact is not the source of truth. It omits anything about permissions, limits beyond the schema's cap, or ordering of results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose and reasonably tight, roughly 80 words with no filler. The mid-sentence list of returned fields is dense and the hard line breaks make it read as a run-on, but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A read-only search tool with a full schema and an output schema; the description covers purpose, scope, output shape, reliability caveat, and next step. The one gap is what happens when 'part' is left empty (project-wide search versus document-scoped), which must be inferred from the schema defaults.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so 3 is the floor, but the description genuinely adds meaning: the 'part' parameter's effect is explained as searching the part plus its base part so a concrete MPN also surfaces datasheet facts. That inference is not derivable from the schema text alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Find values that were read before'), ties it to the sibling that creates them (save_fact), and describes the search domain (the part's documents plus its base part's documents). An agent can distinguish this from find_parts, search_text, or part_parameters without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear workflow: use it to retrieve previously saved facts, verify important values against the original, then record the verdict with set_fact_status. The follow-up tool is named explicitly. It stops short of stating exclusions against alternatives like search_text or get_element_text for raw document inspection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.