resolve_process_incident

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is covered. The description adds real value beyond them: the concrete effect of each mode (retry re-attempts, abandon terminates the path, substitute_output must match the step's format) and the audit consequence ("Fica na trilha quem resolveu"). It does not spell out irreversibility of abandon or repeat-call behavior, which would have pushed this higher.

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?

Front-loads the action and subject, then the trigger condition, then the choice set, then the exclusion. Every clause carries information — no filler, no restatement of the title, and the bolded capitalization of INCIDENTE/NÃO makes the key constraints skimmable.

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, non-idempotent mutation with a nested object parameter and no output schema, the description covers the decision space, the per-mode outcome, the exclusion boundary, and the audit trail. Remaining gaps are the return shape and any authorization requirement implied by "em nome da empresa", which is hinted at but not stated.

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 coverage is only 50%, and the description compensates for the most important field by explaining what each of the three resolution values does and that substitute_output must be validated against the step's format. However, instance_id is undocumented in both schema and description, and the description never says where to obtain it or how task_id pairs with multi-incident instances beyond restating the schema note. Adequate but leaves a real gap.

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 and resource ("Resolve um INCIDENTE de uma instância de processo") plus the acting scope ("em nome da empresa"), and enumerates the three resolution modes inline. It also explicitly carves out what it does NOT handle (approvals and information requests), so an agent can distinguish it from list_approvals or get_process_instance without opening a schema.

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 triggering conditions ("etapa parada por falha, tentativas esgotadas, efeito incerto") and an explicit exclusion ("Aprovações e pedidos de informação NÃO são resolvidos por aqui"). The gap is that the exclusion points to "quem a política designa" rather than naming the actual sibling tool the agent should call instead.

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