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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the description reinforces that. It adds value by stating 'Irreversível' and 'ATO FISCAL REAL', making the consequence explicit. No contradiction with 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 two sentences with zero filler. It's front-loaded with the action and immediately conveys critical constraints.

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's complexity (irreversible fiscal action), the description covers essential aspects: what it does, irreversibility, and prerequisites. It lacks detail on return values or error handling, but since there's no output schema and the action is straightforward, this is acceptable.

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%, but with only 3 parameters where only 'ids' is required, the description explicitly mentions that 'ids' is used to select MDF-e(s). It clarifies that 'account' and 'empresa_id' are likely context identifiers, though not detailed. The description adds meaning about the primary parameter.

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: cancels one or more MDF-e (by id) with SEFAZ. The verb 'cancela' is specific, the resource (MDF-e) is named, and it distinguishes from siblings like emitir, encerrar, excluir.

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 gives clear context: it's an irreversible fiscal act, requires allow_writes and mdfe_tenant_id, and targets MDF-e. However, it doesn't explicitly contrast with alternative tools like hivecloud_mdfe_encerrar or hivecloud_mdfe_excluir beyond listing the purpose.

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