ml_similar_incidents

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

Annotations already declare readOnlyHint and openWorldHint, so the description adds context about returning resolved incidents ranked by keyword match count. It does not elaborate on potential edge cases (e.g., both parameters provided) but adds moderate value beyond annotations.

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?

Two well-structured sentences that front-load the purpose and immediately convey usage. No unnecessary 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?

No output schema, but description provides essential info: returns resolved incidents ranked by keyword match count. Lacks details on output format (e.g., list of sys_ids or full records), but sufficient for a read-only search tool. Could be more complete.

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% with parameter descriptions. The description clarifies the mutual exclusivity of incident_sys_id and short_description, and mentions that limit controls max results. This adds meaning beyond the schema.

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 finds similar past incidents using keyword-based matching, with two distinct modes (by incident sys_id or by short_description). This differentiates it from sibling tools like get_incident or ml_auto_categorize.

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 explicitly instructs to provide either an incident_sys_id or a short_description, indicating mutual exclusivity. It states the output is resolved incidents ranked by keyword match count. While it doesn't mention alternatives or when not to use, the context is clear.

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