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

Annotations already establish readOnly and closed-world, and the description adds real context beyond them: no external model is called, deeper search widens candidates per index without increasing result count, and ranking may change with no guarantee of better relevance. It leaves result ordering and pagination behavior unstated, but that is largely covered by the output schema.

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?

Information is front-loaded with the mechanism first, then the caveat, then the follow-up pointer to ler_pagina. The sentences are dense but each carries a distinct fact; minor redundancy exists between the description and the profundidade schema text.

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 a full output schema and solid annotations, the description supplies what structured fields cannot: the fusion mechanism, the closed-world/no-external-model guarantee, and the risk profile of the tuning parameter. Nothing essential for correct invocation appears missing.

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 baseline is 3; the description earns an extra point by explaining the operational trade-off of profundidade (only for low-coverage investigation, ranking instability, no guaranteed gain) rather than restating its bounds. The pergunta and limite parameters are left entirely to the schema, which is acceptable at full coverage.

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 operation: it fuses lexical and semantic local search by RRF (k=60) and returns sources, positions, indices and states. The word 'híbrido' plus the fusion mechanism clearly separates it from purely semantic or page-lookup siblings, though it never names buscar_semantico or buscar_paginas explicitly.

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 a clear conditional rule for the optional profundidade: only when investigating low coverage, with the warning that the ranking may shift and improvement is not guaranteed. It also routes the agent to ler_pagina for verification, but does not state when to prefer this over the semantic-only sibling.

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