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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the description only needs to add context. It adds useful behavioral details: query accent/case handling, relevance ordering, empty-list semantics, and in-memory caching of a public catalog. It avoids contradicting 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 organized in short, labeled chunks (core behavior, contract context, exclusion, query guidance, safety). Every sentence contributes either to selection, invocation, or routing, and the most important information is front-loaded in the first sentence.

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 one-parameter search tool, the description is complete: it defines the return type and count, explains the empty-list case, shows how to use results with `fetch`, and warns against using it for data queries. An agent has everything needed to call it correctly without further inference.

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%, so the schema already documents the `query` parameter. The description still adds one meaningful fact beyond the schema — that queries may be in Portuguese or English — while restating that natural language/keywords and accent/case insensitivity are acceptable. This is enough to move above the coverage baseline.

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: it searches the Banco Central do Brasil SGS catalog and returns up to 10 matching documents with a concrete shape. It also distinguishes itself from siblings by stating it is a catalog index, not a data query tool.

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 explicitly says when to use this tool (Deep Research workflows via Responses API), names the downstream `fetch` step, and tells the agent to prefer `bcb_*` tools for actual data. This is clear routing guidance with exclusions, not just an implied context.

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