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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description adds meaningful behavioral detail beyond them: no new inference or aggregation, snapshot-limited coverage, empty data array on no match, and argument errors on invalid input. This gives the agent a clear picture of what will and will not happen.

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?

The description is appropriately sized and front-loads the core purpose in the first sentence. The behavioral notes and return format are dense but useful. There is minor redundancy ('Inputs: query' and 'Required: query') but it does not significantly detract.

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?

Given there is no output schema, the description compensates well by naming the return structure (source_class, provenance, snapshot, pagination, limits) and edge behaviors (empty array, argument error). Combined with fully documented parameters, an agent has enough context to invoke and interpret results correctly.

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 schema fully documents all four parameters, including query matching semantics, pagination limits, and snapshot behavior. The description only restates that query is required and mentions 'Inputs: query', adding no substantive parameter meaning beyond the schema.

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?

The description clearly states a specific verb ('Find') and resource ('policy and document facts'), with a precise lookup method ('by title or document-number text'). It distinguishes this from analytical or inference tools by emphasizing 'Recorded facts only', but it does not explicitly contrast itself with sibling search tools like search_recalls or search_standard_metadata.

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?

The description gives clear context for when this tool is appropriate: only for recorded policy/document facts, not for inference or aggregation. It also sets expectations about snapshot coverage. However, it does not name alternative tools or state explicit exclusion conditions, leaving some routing to inference.

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