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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial behavioral detail beyond them: the exact returned fields, that links may point to a public blog page or an app page requiring login/skip, the default limit of 5 with a max of 10, the special crisisReferral handling rule, and a privacy constraint on the query. This is rich context that materially shapes correct invocation and response handling.

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 purpose and key constraints are front-loaded, and every sentence carries operational or safety value. It is a single dense paragraph and slightly restates return fields already present in the output schema, which costs a little efficiency but does not bloat the definition.

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 search tool with three parameters, 0% schema description coverage, and an output schema, the description supplies everything an agent needs: parameter behavior, return shape, link/auth caveat, privacy rule for query construction, and mandatory crisisReferral display behavior. Nothing critical is left unexplained.

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 0%, so the description must carry the burden. It explains all three parameters: query content/style and privacy limits, type as the format filter, and limit's default (5) and ceiling (10). Only the enum values themselves live in the schema, but the description maps type to its meaning adequately.

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 ('Busca, pelo texto da consulta') and resource ('conteúdos de psicoeducação publicados no Namandu'), and enumerates the content formats it covers (artigos, exercícios, vídeos, áudios, materiais, guias). It does not explicitly contrast itself with siblings like search_scientific_literature, so an agent must infer the distinction from scope alone.

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 concrete usage context: how to phrase the query ('Escreva a consulta com os temas, como "ansiedade antes de dormir"'), what not to include (identifying data), and a boundary ('não é diagnóstico nem indicação clínica'). It stops short of naming alternative tools or stating when another sibling should be used instead.

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