find_similar_incidents

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

With no annotations, the description discloses meaningful behavior: it ranks resolved incidents with close notes higher, includes closed records, and performs fuzzy keyword matching. It doesn't explicitly state it is read-only, but the search semantics and lack of side effects are clearly conveyed.

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 front-loaded with the core purpose, followed by use cases, a compact Arg list, and a sibling comparison. Every sentence earns its place and there is no filler.

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?

The tool's purpose, use cases, parameter behavior, and differentiation from search_incidents are all covered. With an output schema present, the absence of return-value details is acceptable, making the description complete for correct invocation.

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?

Despite 0% schema description coverage, the 'Args' block explains each parameter's intent: problem_description as natural-language symptoms, cmdb_ci as a filter that boosts matching incidents, and limit with a 1-20 range. This adds practical meaning beyond the bare type declarations.

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 opening line 'Find PAST incidents resembling a described problem, ranked by similarity' states a specific verb, resource, and output behavior. It distinguishes itself from sibling search_incidents by noting the fuzzy keyword match over history and inclusion of closed 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?

Explicitly states when to use it: 'has this happened before?' and finding the fix that worked last time. It also says to use it for duplicate detection before calling create_incident, and contrasts with search_incidents by explaining the alternative's exact field filtering.

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