buscar

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

No annotations exist, so the description carries the burden and does disclose useful behavior: results include file and exact page, it works by meaning and by identifier, and 'arquivo' scopes the search to one PDF. It omits permission/rate-limit behavior but adds a verification workflow that shapes safe usage.

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 purpose and then the output/citation contract, with the 'arquivo' usage note last. Dense but mostly efficient; the examples add value rather than padding.

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 return-value detail is not needed, and the citation/verification workflow compensates well. However, top_k and rerank materially affect search results and are unexplained in both schema and description, leaving a real gap for a semantic-search tool.

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 0% and only one of five parameters is explained: 'arquivo' (optional, restricts to a single PDF, useful in multi-volume cases). caso, query, top_k, and rerank carry no meaning beyond their bare titles, leaving the retrieval-tuning parameters undocumented.

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 (busca) and resource (documentos do caso), and clarifies the dual mode 'semântica + literal' with concrete examples. It also names the sibling relationship with obter_pagina for verification, so an agent can distinguish its role from the other case-level tools.

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?

Gives clear operating context: always cite '(arquivo, p. N)' and verify with obter_pagina before asserting sensitive facts, and use the 'arquivo' filter for multi-volume cases. It stops short of explicit when-not-to-use or direct alternative routing (e.g., vs indice_pecas or cronologia).

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