Search

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description still adds non-structured behavior: relevance-ranked ordering and inclusion of surrounding messages per hit. It also discloses the literal-token matching model, which prevents an agent from expecting semantic recall. It does not mention cost, limits, or empty-result behavior.

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 tight sentences: the first states the operation, ordering, and return shape; the second gives a practical caveat with a concrete example. Nothing is redundant with the name or title and the core behavior 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?

With an output schema present, the description needn't explain return values, and it still usefully notes ranked order and context windows. For a 5-parameter tool it leaves the limit cap and the interaction between chat/since/until filtering unaddressed, but the essential call semantics are covered.

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 80% and the query parameter's syntax (exact phrase, prefix*, OR, accent-insensitive) is already in the schema. The description adds meaning beyond it by framing matching as literal words rather than meaning, which drives synonym-expansion behavior. The undocumented limit parameter is not clarified in the description.

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 por palavras nas mensagens") plus two distinguishing traits: results are ordered by relevance and each hit is returned with surrounding messages. It never names a sibling, so the agent must still infer why to pick this over get_messages, which keeps it below 5.

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 second sentence gives real querying advice (literal matching, so retry with synonyms like "entrega"/"sexta" for "prazo"), which shapes how an agent should call it. However there is no when-to-use/when-not guidance relative to the siblings (get_messages, list_chats), so selection is only implied.

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