list_models

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

With no annotations, the description must carry behavioural disclosure. It does add a useful data-provenance caveat ('expõe somente capacidades e preços publicados pelos endpoints'), implying no local inference or estimation, but it never states the operation is read-only, that results may be cached, or what the response shape is.

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 short sentences, front-loaded with the verb and resource, with no redundant restatement of the tool name. Nothing is wasted.

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 three-parameter tool with zero schema description coverage and no annotations or output schema, the description is too thin. An agent cannot learn from it what search does, what refresh invalidates, or what the returned catalog entries contain.

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% and the description never mentions type, search, or refresh. Only an indirect hint exists ('modelos de imagem e vídeo' loosely maps to the type enum), leaving the search filter and especially the refresh/cache-reset flag completely unexplained.

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 (consulta) and a specific resource (catálogos atuais de modelos de imagem e vídeo do OpenRouter), which clearly separates it from the generation/estimation siblings. It does not explicitly name an alternative, but the read-only catalog framing is 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?

Usage is only implied: 'catálogos atuais' suggests discovery of available models, but there is no statement about when to prefer this over estimate_cost or before calling generate_image/generate_video. No exclusions or prerequisites are given.

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