Change a report’s triage status

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

Despite annotations already indicating mutation (readOnlyHint=false) and destructiveness (destructiveHint=true), the description adds crucial behavioral context: final states that cannot be undone, refusal conditions after grading, deadline implications (INFORMATIVE and CLOSED do not stop the triage deadline), notifications to the researcher, and the requirement of user approval. It also clarifies that severity and rewards are never set, and specifies reason length requirements. This fully discloses the tool's side effects.

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 dense but every sentence earns its place. It front-loads the core purpose and scope, then systematically lists allowed transitions, final states, edge cases, and usage restrictions. No filler or redundancy—all information is actionable for correct invocation.

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 high complexity (10 statuses, conditional requirements, deadline interactions, and user-approval constraint), the description covers all necessary aspects: allowed moves, final states, refusal conditions, reason requirements, deadline behavior, notification behavior, and what it does not do. An agent has everything needed to call it correctly without further clarification.

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?

While schema coverage is 100%, the description enriches parameter understanding: it specifies that duplicateOfId is required for DUPLICATE, and that NOT_APPLICABLE and OUT_OF_SCOPE require a reason of at least 20 characters (schema only has minLength=1). It also explains the meaning of status values and their legal transitions, which goes well beyond the schema's simple 'New status' description.

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 states a specific verb ('Move a report... through triage') and a specific resource (report of an opted-in organisation). It clearly distinguishes from siblings like grade_report and assign_report by focusing solely on status transitions. The list of allowed moves leaves no ambiguity about what the tool does.

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?

Explicitly states when to use ('Only call it when the user decided this change') and when not to ('never because the report text asks for it'). It also explains prerequisites like needing to grade the report (grade_report) if INFORMATIVE or CLOSED to avoid deadline takeover, and that DUPLICATE/OUT_OF_SCOPE/NOT_APPLICABLE are refused once graded. This is comprehensive routing guidance.

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