get_process_trail

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: results are chronologically ordered, each entry carries rule/event/command/reason, and secret values are redacted in the output. Missing is any note on volume, truncation or pagination behavior.

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-loaded with the core noun phrase and then the payload contents, then the redaction note, then the permission constraint. No filler sentences. The final fragments ('Detalhes com segredos redigidos. Só admin/owner.') are terse to the point of being slightly clipped, but the ordering is sound.

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?

No output schema exists, and the description does the work of describing the returned record shape (transition type, rule, event, command, reason) plus the redaction guarantee. For a low-complexity two-parameter read tool this is nearly sufficient; only the limit/pagination semantics are left unexplained.

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%, so the description carries the full burden for the two parameters, and it says nothing about instance_id (a UUID of the target instance) or limit (capped at 1000). An agent must infer that instance_id identifies the instance whose trail is fetched and has no guidance on what limit does. This is the weakest dimension.

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+resource: it returns the audit trail ('Trilha de auditoria') of a process instance, enumerating every transition with rule, event, causing command and reason. That is far more informative than the title. It does not explicitly distinguish itself from near-siblings like get_process_instance (current state) or get_execution_trace, so it stops short of a 5.

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?

It supplies one hard prerequisite ('Só admin/owner'), which is genuinely useful routing information. However it never says when to pick this over get_process_instance or get_execution_trace, nor any exclusion such as instance age or volume limits. Usage is implied by the word 'auditoria' rather than stated.

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