obter_evidencia

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

With no annotations, the description carries the full burden and does disclose real behavioral traits: pagination via offset, text wrapped in official-document delimiters, enumerated status values, and the crucial scope limit that a capture proves the origin of bytes but neither validity nor legal judgment. It does not say whether it is read-only or what happens with an invalid/expired capture_id, which keeps it below 5.

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 output/what-you-get statement is front-loaded, and the usage and caveat sentences follow in a sensible order with no filler. The parenthetical asides and line-broken status enumeration make it slightly less scannable than it could be.

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 structure need not be re-explained; the description still covers purpose, pagination, status semantics, and evidentiary limits, which is what a three-parameter read tool needs. The remaining gap is error/edge behavior for a bad capture_id, which the agent would have to discover at call time.

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 must compensate, and it only partly does: it explains that capture_id comes from other tools and restates the 50,000 max_chars ceiling already encoded in the schema. The offset parameter, the core of the pagination contract, is never explained, so half the parameters remain opaque.

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 first sentence names the specific resource: metadata of an official capture (url, hash, date) plus the extracted text, paginated between document delimiters. That is a concrete verb+resource statement an agent can act on. It stops short of 5 because it never names a sibling tool (e.g. resolver_citacao or obter_dispositivo) that would be the alternative when a capture_id is not in hand.

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?

"Use para conferir de onde veio um resultado (capture_id vem de outras ferramentas)" gives a clear trigger and tells the agent where the required id originates. The caveat that status=unavailable means the capture is missing rather than the document not existing is a useful anti-misuse rule. No explicit exclusions or named alternatives, so it falls short of 5.

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