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

Annotations already cover read-only/idempotent/non-destructive, and the description adds real value on top: it reuses the same acesso_codigo as the reading, triggers no new AI analysis, and discloses the partial-data/coverage semantics plus the important caveat that an unfinished dossier is not evidence a requirement is absent. That is substantive behavioral context beyond structured fields.

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?

Written as a run-on string of fragments with no front-loaded statement of what the tool does; safety caveats and access notes are interleaved before the reader knows the purpose. Multiple sentences ('It does not start AI.', 'It does not start AI... with no new analysis') restate the same point.

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?

At 8 parameters with no output schema, the definition covers auth and coverage semantics but leaves the return shape vague — 'inspect complete, coverage and issues' gestures at output fields without describing them, and the pagination cursor ('after' = previous `next`) implies a next-token response that the description never mentions.

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%, including the credential parameters and the kind filter, so the description need only complement it. The only added semantics is that acesso_codigo mirrors the reading access, which the schema already explains at length; baseline 3 applies.

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 enumerates the resource content well (items, requirements, attestations, deadlines, obligations, with conditions/exceptions/excerpts), so an agent can infer what comes back. But there is no clean verb+resource statement and no explicit differentiation from nearby siblings like get_document, get_deadlines, get_reading_manifest or get_qualification — the reader has to piece the purpose together from scattered clauses.

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?

Useful cues exist: start from the prepared dossier instead of rebuilding extraction, an export requires a finished version, check the original and source dates before a bid decision, and 'does not start AI' implies no new cost. However, none of these are framed as 'use this tool when X, use sibling Y when Z', so the routing guidance stays implicit and buried.

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