categorize_incident

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

The description explains that this tool works through the Table API analyzing similar resolved incidents, which is a heuristic approach as opposed to a model-based one. It discloses the limitation that PI has no public REST prediction endpoint, giving the agent important context about what this tool does and does not do. With readOnlyHint=true and openWorldHint=true annotations already present, the description adds meaningful behavioral nuance about the heuristic mechanism and PI limitation.

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 a single compact sentence that efficiently conveys purpose and key limitation without redundancy. The PI limitation note is relevant and earns its place. Slightly more structure could help, but the density of useful information is high with no wasted words.

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 has 100% schema coverage, readOnly/openWorld annotations, and no output schema, the description adequately covers the heuristic approach, the PI limitation, and expected outputs (category, assignment group, priority). It doesn't describe return format, but without an output schema and with the outputs named, this is acceptable completeness for a suggestion-type tool.

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 100%, so both parameters (short_description and description) are documented in the schema. The description adds minor value by noting that description is 'not required for the heuristic' and that short_description is the primary input. This clarifies the minimal input needed but doesn't go beyond what the schema already provides in terms of parameter meaning.

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 suggests category, assignment group, and priority for an incident by analyzing similar resolved incidents via Table API. The verb 'suggest' combined with the three specific outputs (category, assignment group, priority) gives a clear purpose that distinguishes it from sibling incident tools like resolve_incident or close_incident.

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 provides useful context about what to use instead - it explicitly notes that Predictive Intelligence has no public REST prediction endpoint, and for model-based scoring the agent should run PI on-record and read the predicted field. This offers practical guidance for when alternatives are needed, though it doesn't fully spell out when to choose this tool versus the ml_auto_categorize or ml_similar_incidents sibling tools.

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