cancel_process_instance

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

Annotations already declare destructiveHint=true and idempotentHint=false, so the description is not required to establish that this is a mutation. It adds genuinely new behavior: the actor is recorded in the audit trail and the originating conversation gets a closure notice — side effects an agent could not infer from structured fields.

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?

Three tight sentences, front-loaded with the verb and the key qualifier. The parenthetical example and capitalized emphasis are mildly noisy but each sentence contributes distinct information (purpose, audit, side effect).

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 destructive two-parameter tool with no output schema, the description covers who may do this, why, and the two observable consequences. It omits irreversibility and permission requirements, but the core invocation context is present.

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 description never mentions instance_id or reason_note. Schema coverage is only 50%: reason_note is documented inline, but instance_id carries no description anywhere, and the description does not compensate for that gap or clarify format/scope of the identifier.

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 ('Cancela') and resource ('instância de processo') plus a qualifier that separates it from a user-initiated cancel: it is done 'EM NOME DA EMPRESA' as an admin intervention. An agent can distinguish it from resolve_process_incident or cancel_agent_turn, though no sibling is named explicitly.

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?

Gives concrete selection conditions with two examples ('dono saiu', 'o pedido não faz mais sentido') that frame this as an administrative override rather than a routine cancel. It does not name an alternative tool or state a hard when-not, which keeps it short of a 5.

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