consult_reference

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

Annotations only cover readOnly/openWorld, so the description does the heavy lifting: it discloses that results are UNTRUSTED hints, that each fact is flagged for whether a source was attached (with source text), and that probably-living people are withheld and counted. This is exactly the behavioral context an agent needs to interpret and trust the output correctly.

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

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

Front-loaded with the core statement, then the trust model and workflow directive. Every sentence carries information, though the source-flag sentence is a slightly long construction that could be tightened without losing meaning.

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

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

For a read-only search tool with no output schema, the description adequately explains what comes back (per-file individuals, facts, source flags) and the privacy behavior. It does not discuss result limits, pagination, or how many files are scanned, which is a minor remaining gap.

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

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

Schema description coverage is 100%, so the four parameters are already fully documented in the schema; the description adds no syntax or matching detail beyond it. It does clarify why include_private matters ('Probably-living people are withheld and counted'), but that is general context rather than added per-parameter semantics.

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

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

States a specific verb ('consult') and resource ('legacy GEDCOM reference layer') and immediately scopes it: it searches configured Ancestry/FamilySearch exports and returns matching individuals and claimed facts. This clearly distinguishes it from siblings like search_people/query_records, which operate on the tree itself rather than the external reference layer.

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

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

Explicitly states when to use the results ('use them to decide what real record to hunt for, then create the fact in the tree citing that record') and when not to ('do not copy a hint in as a sourced fact'). The authoritative-vs-hint distinction tells the agent exactly how this tool fits into the citation workflow without naming every sibling.

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