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

Annotations already convey readOnlyHint=false, and the description's '[write, altera dados]' essentially restates that this is a write operation. It does not disclose whether the operation is reversible, whether the charge is physically removed or merely marked as excluded, or what side effects occur. destructiveHint=false is not clearly contradicted because the operation may be a soft delete via PUT, but the description adds minimal behavioral depth beyond the annotations.

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 a single sentence plus tags, making it very concise and front-loaded with the action. The trailing tags are somewhat redundant with annotations but do not hurt readability. It is appropriately short for a simple operation, though the brevity contributes to missing semantic context.

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 no parameter descriptions, no output schema, and minimal behavioral disclosure, the description leaves essential invocation details unspecified. The agent must guess what to put in body and query and what account refers to. The description is insufficient for correct tool invocation.

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 three parameters (body, query, account) are only typed as strings with no descriptions. The tool description does not mention any of these parameters or provide format expectations. An agent has no way to construct a valid request from this definition.

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 explicitly states the action 'Excluir uma cobrança' (delete a charge) and includes the endpoint 'PUT /cobranca/excluir', making the operation clear. The verb 'excluir' distinguishes it from sibling operations like 'estornar' or 'desinvalidar', though it does not name alternatives. It is a precise, actionable statement, even if it closely mirrors the tool name.

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?

No guidance is provided about when to choose this tool over sibling cobrança operations such as estornar, desinvalidar, or liquidar. The only contextual cue is the tag '[write, altera dados]', which merely indicates a write operation, and 'Receitas' (Revenue) suggests a domain but not selection criteria. An agent cannot determine the appropriate scenario from this description.

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