Busca para Deep Research

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

Annotations already cover read-only, idempotent and non-destructive, so the description only needs to add context — and it does: results are cached in memory from the public source, an empty list signals no match, and the index is explicitly not a data source. It does not discuss ranking mechanics or catalog staleness, but the annotation burden is already met.

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 what the tool does and returns, then guidelines, then query semantics, then behavior — a sensible ordering with no true filler. However, the accent/case sentence duplicates the schema and the Deep Research contract paragraph is longer than the routing information it carries.

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 values need no expansion, and the description still summarizes cardinality and ordering. For a single-parameter search tool sitting inside a 22-tool catalog, everything an agent needs to select it, query it, and route its output is present.

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 100% and the single `query` param is already documented in the schema, including the accent/case insensitivity the description repeats. The description's only marginal addition is that Portuguese or English both work, which is a small gain over the structured field — 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?

States a specific verb and resource — searches the IBGE catalog — and pins the exact return shape ({ id, title, url }, up to 10, relevance-ordered). It explicitly distinguishes itself from siblings by naming the ibge_* data tools and fetch as the downstream consumer of returned ids.

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 explicit when-to-use (OpenAI Deep Research / Responses API contract requiring exactly `search` and `fetch`), when-not-to-use (direct questions and data/values/rankings should go to ibge_sidra, ibge_cidades, ibge_indicadores, ibge_comparar), and the follow-up action (pass a returned id to `fetch`).

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