Find Related Incidents

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

Annotations already carry readOnly/openWorld/non-destructive, so the description's added value is the clamping behavior for max_results ('clamped and reported, not rejected'), which directly affects how an agent should size arguments. It omits anything about similarity_threshold's effect on recall, keeping it from a 5.

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?

Front-loaded one-liner followed by scannable bullets and a short input/argument paragraph; every sentence carries information. The emoji and 'CRITICAL' emphasis are minor noise but don't obscure the content.

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?

For a 5-param read-only search tool with an output schema (so return values need no explanation), the description covers invocation mode, filtering, and argument bounds. The one gap is the similarity_threshold knob, which is neither explained here nor in the schema.

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?

With 60% schema coverage, the description compensates: it gives the either/or rule for incident_id vs incident_description with example descriptions, explains status_filter semantics (empty = all), and restates the max_results bound plus clamping. Only similarity_threshold is left to 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?

States a specific verb and resource (find historically similar incidents) plus the mechanism (ML similarity analysis), which clearly separates it from list_incidents/search_incidents style sibling tools. It stops short of naming a sibling alternative explicitly, so it doesn't reach the top of the scale.

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 WHEN TO USE block gives four concrete triggers (early in response, unclear root cause, before escalation, post-incident analysis) and the body explains the either/or input constraint. An agent knows both when and how to invoke it.

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