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

The description adds minimal behavioral info beyond 'creates'. Annotations indicate it is a write operation (readOnlyHint=false) but not destructive, which the description reinforces by the word 'cria'. However, it doesn't disclose what happens on success (e.g., returns created object), error conditions, or side effects. Since annotations already provided the safety profile, this adds little.

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 description is concise and to the point, consisting of a single clear sentence. It lists required fields succinctly. However, it lacks structured sections, examples, or format guidance. Still, it conveys the essential information with minimal fluff.

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?

The description lacks important context: what the tool returns, error conditions, validation rules, or any behavior beyond creation. It doesn't mention the data source or system it operates on, nor provide any guidance on integration with other tools. The minimal information leaves the agent guessing about the outcome of the operation.

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?

The required fields are listed (nome, status, responsavel, cliente), but there are no descriptions for any parameter. The schema shows types (string/number) but for a create operation, it's unclear what format 'status' should take (e.g., is it a number code or string?), what 'cliente' expects (ID or name?), or what 'extra' contains. Optional fields like 'valor_total' and 'data_atendimento' are 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?

The description clearly states the tool's purpose: 'Cria oportunidade' (creates opportunity). It identifies the action as creation, which distinguishes it from get/list tools. However, it doesn't explicitly differentiate from other create tools like create_processo or create_pessoa, but the resource is named.

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 description mentions required fields but gives no guidance on when to use this tool versus alternatives, nor does it mention prerequisites or context. It doesn't say when not to use it or what scenarios it's best suited for.

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