ml_auto_categorize

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

The annotations provide readOnlyHint and openWorldHint, but the description adds valuable behavioral context: it queries the last 500 resolved records, groups by category, and matches keywords. This explains the mechanism and the 'suggest' nature of the output, going beyond what annotations alone convey.

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 two sentences, front-loaded with the purpose, and contains no fluff. It efficiently communicates both what it does and how it works without redundancy.

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 no output schema, the description adequately explains the outcome ('suggest a category') and key behavior. It lacks details on return format or confidence but is sufficient for a read-only ML tool. A minor gap is not explicitly stating the dependency on resolved records, though it is implied.

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?

Input schema covers all three parameters with descriptions, so baseline is 3. The tool description adds meaning by explaining how parameters are used (e.g., 'matches input keywords' ties short_description to the matching logic, and the mention of 'table' as analysis scope). This is modest but useful.

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 a specific verb+resource: 'Auto-categorize a record based on its description by analysing resolved records of the same table.' This distinguishes it from sibling tools like categorize_incident (which is incident-specific) by emphasizing table-agnostic analysis and the use of resolved records.

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?

No explicit guidance is given on when to use this tool versus alternatives like categorize_incident or ml_similar_incidents. The description implies usage for auto-categorization with ML, but provides no exclusions, prerequisites, or alternative comparisons.

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