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

Goes well beyond the annotations: no network or inference, OAuth machine scope pesquisa:consultar required, offsets in UTF-8, proofs and per-source failures returned, score is not a probability, and the tool does not certify normative vigência. These are exactly the caveats an agent needs and none are derivable from readOnlyHint/idempotentHint.

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 ranking mechanism, then inputs, then outputs, then caveats and auth. Dense but nearly every clause carries information; only the default limit and cap are omitted for the schema to handle.

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?

An output schema exists, so the brief mention of returned offsets, hashes, proof and per-source failures suffices. Auth scope and the non-certification caveat are covered; the only gap is that it does not say when this tool is the wrong choice versus its retrieval siblings.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning: the four source fields must be exact matches, the source list is bounded to 1-4, and referencia_em excludes acquisitions after the UTC day (a semantic the schema leaves undocumented). The limite parameter's default and cap are left to the schema, which is fine.

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?

Opens with a specific verb and resource plus the ranking method (BM25 lexical over literal excerpts, local, no network or inference), which distinguishes it from retrieval siblings like buscar_hibrido and buscar_semantico by mechanism. It stops short of naming an alternative explicitly, so the differentiation is implied rather than routed.

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 prescribes the call shape (query plus 1-4 sources with exact ref, source_ref, receipt_sha256 and url_declarada) and notes referencia_em as optional, which implies usage. But it never states when to prefer this over buscar_hibrido, buscar_semantico or pesquisar_fontes, and no exclusion condition is given beyond the local/verified constraint.

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