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

Annotations already mark readOnlyHint=true and destructiveHint=false; the description adds meaningful behavior: multiple termos are searched separately with staggered delays to avoid rate limits, results are merged and deduplicated, broad terms can overwhelm the source, and antecipagov=true switches to a different database. No contradiction with annotations.

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 front-loaded with the purpose and return fields, then adds parameter behavior and a warning in a compact block. Every sentence contributes: search scope, outputs, intended use, multi-search semantics, and a caution about broad terms.

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?

For a 6-parameter read-only search with no output schema, the description covers the core selection and invocation needs: result fields, dangerous input patterns, batch behavior, and the special antecipagov mode. The main gap is pagination/page semantics, which would be needed for a fully complete invocation guide.

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?

With schema description coverage at 0%, the description compensates well for most parameters: it explains termos[] (multiple independent searches, merged/deduped), the search criteria (nome, UF, portal), and antecipagov behavior. However, 'pagina' is not addressed and the 'portais' values are only implied, so it is not fully complete.

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 opens with a specific verb and resource: 'Busca de ÓRGÃOS/entidades compradoras por nome, UF e/ou portal' and states the returned fields (portal, UF, uasg, nome, payment info). This clearly differentiates it from sibling search tools by focusing on the buyer-entity registry.

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?

It explains the practical use: 'Útil pra achar o órgão e usar o filtro em outras buscas' and gives explicit guidance to avoid broad terms, preferring UF/portal or specific names. It does not name direct alternatives, so it misses the top-level 'when-not to use this versus sibling' exclusion, but the context is clear.

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