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

Annotations already declare readOnlyHint=true, so the tool is known to be side-effect-free. The description adds the semantic mechanism (vector embedding, cosine similarity) and the fact that it returns page paths, which enriches the behavioral model without contradicting the annotations. It does not detail pagination or rate limits, but these are schema-managed.

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 two sentences, tightly packed with essential information: the core operation, the distinguishing characteristic, the usage trigger, and the output's purpose. There is no redundant language, and the main purpose is front-loaded.

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?

Given the tool's moderate complexity, an output schema exists (though not shown), and annotations cover safety, the description covers purpose, usage, and downstream action. It omits niche details like error cases or performance, but nothing critical for an agent to invoke it correctly is missing. A small gap is not explicitly mentioning how the 'limite' interacts with returns, but the schema handles that.

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%, and the schema already provides clear descriptions for all three parameters (pergunta, area, limite). The description does not add parameter-level guidance beyond the schema; it briefly reinforces that 'pergunta' is a natural-language question but no new information. Thus the baseline of 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 uses a specific verb ('Busca') and resource ('páginas do acervo') and clearly contrasts with the lexical sibling 'buscar_paginas' by emphasizing semantic vs. lexical matching. It also names the downstream consumer 'ler_pagina', making the tool's role unambiguous.

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?

The description explicitly states when to use it: when lexical search ('buscar_paginas') fails due to vocabulary mismatch. It also indicates that the returned paths feed into 'ler_pagina', providing a clear usage flow. This is direct and actionable for an agent.

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