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

Annotations indicate readOnlyHint=false, destructiveHint=false, idempotentHint=false, but the description adds '[write, altera dados]' (write, changes data), which is somewhat redundant but clarifies the write nature. However, it does not disclose what happens when cancelling (e.g., irreversibility, effects on financial records) or any error cases. With limited annotation coverage, the description should carry more behavioral detail but does not.

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 very short, only two sentences. It includes the endpoint and a note on bulk support. It is front-loaded but so concise that it lacks key details. It is not overly verbose, but the brevity costs clarity.

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?

Given the tool is a mutation (cancel service invoice) with no output schema and 4 parameters, the description is incomplete. It does not explain return values, error handling, or the meaning of 'body' and 'account'. Compared to the calibration examples, a cancellation mutation with zero parameter descriptions and minimal behavioral disclosure is inadequate.

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%, meaning the schema has no descriptions. The description only mentions 'ids' for bulk support, but does not explain the 'id', 'body', or 'account' parameters. The required 'id' is not explained beyond the endpoint path. For a mutation tool, this is insufficient. The description does not compensate for the lack of schema descriptions.

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 this tool cancels service invoices via a specific endpoint (POST /api/notas_fiscais_servicos/cancelar/{id}). However, the verb 'Cancelar' and resource are clear, but it does not explicitly distinguish from the sibling tools like gestaoclick_notas_fiscais_consumidores_cancelar_create or gestaoclick_notas_fiscais_produtos_cancelar_create, although the resource 'servicos' is implied. It has a specific verb+resource but lacks explicit sibling differentiation.

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 'Bulk support: accepts ids for batched execution', which implies when to use bulk mode. However, there is no guidance on when to cancel versus other operations like emitir (issue) or delete. No explicit alternatives or exclusions are provided.

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