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

Annotations convey readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the tool is a safe read operation. The description adds the specific endpoint paths and that it is a GED search, but does not disclose details like authentication requirements, rate limits, or what exactly the download endpoint returns (e.g., binary vs metadata). It does not contradict annotations, but adds limited extra context beyond them.

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 a single sentence that conveys the main purpose and the endpoint. It is concise and front-loaded with the key action, but the inclusion of an endpoint path may be redundant given the resource is already clear. However, no unnecessary fluff.

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 the tool has no output schema, no parameter descriptions in the schema, and the description provides minimal parameter semantics, it is incomplete for an agent to know how to invoke it correctly. The 'query' parameter is completely unexplained, and the download endpoint is mentioned but not detailed (e.g., response format). The description does not cover edge cases like what happens if the code is invalid.

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 0%, so the description carries the burden for parameter semantics. Despite that, the description does not explain the 'codigo' parameter beyond implying it is the code for download, and the 'query' parameter remains completely undocumented. The schema provides property types, but no semantic meaning is added by the description.

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 the tool searches for files/documents (GED) and provides a download endpoint with the code, which distinguishes it from other projuris_get_* tools that target different resources. The verb 'Busca' (searches) and resource 'Arquivos/documentos (GED)' are specific.

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 implies usage by providing the endpoint pattern, but it does not explicitly state when to use this tool vs alternatives. It mentions a download endpoint, which suggests usage for retrieving files, but no explicit 'when not to use' or alternative guidance. Since siblings all are projuris_get_* for different resources, the resource specificity is implicit.

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