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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds meaningful context: how the ranking is produced (cosine over the same embedding model) and what the output is used for. It does not discuss ranking scores, thresholds, or how 'limite' interacts with corpus size, but the safety profile is already covered by 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?

Two dense sentences with zero filler: mechanism and contrast first, then the usage rule and downstream handoff. Nothing repeats the name or title.

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?

With annotations and a full output schema present, the description covers mechanism, selection and follow-up. Minor gaps: no note on how results are ordered when 'limite' is large, or what happens when no page passes a similarity bar.

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%, so 'pergunta', 'area' and 'limite' are already documented with examples and defaults. The description adds no per-parameter syntax or constraints beyond the schema, so the 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 ('Busca páginas do acervo pelo SIGNIFICADO') and explains the mechanism (query embedded as vector, cosine nearest neighbors). It explicitly sets itself apart from the lexical sibling buscar_paginas, so an agent can choose without opening either schema.

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 an explicit selection rule: use it when buscar_paginas (lexical) fails because the vocabulary differs. It also names the downstream step - the returned paths are input for ler_pagina - completing the workflow.

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