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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered and the description contributes nothing new about behavior. It does not say what a missing incident yields (404 vs empty), whether the response is the full incident object, or that describe_operation must be called to learn the request shape. No contradiction with annotations, but no added value either.

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?

It is short, but the first sentence is duplicated word-for-word, which is pure waste, and the remaining content is an opaque operation-id hash plus a pointer to another tool. The only useful token (describe_operation) is buried at the end rather than front-loaded.

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?

With no output schema, 0% parameter description coverage, a nested query object, and no annotations gaps to hide behind, the description should carry the burden and instead carries none. An agent learns only the route and that a sibling tool documents schemas; it cannot tell what the response contains or how to shape the query parameter.

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 description coverage is 0% across two parameters (required params.id and an untyped query object), so the description is expected to compensate and does not. The ':id' path placeholder weakly signals that id identifies the incident, but nothing explains the free-form query object, its allowed keys, or length constraints on id.

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 is the raw HTTP path repeated verbatim twice, identical to the tool title, and adds no framing beyond 'GET /api/support/incidents/:id'. It does not distinguish this from the sibling list tool get_support_incidents or from get_support_incidents_history, and a long generated hash in the name gives no semantic help. This is effectively a restatement of the name/title.

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 only actionable sentence points at describe_operation for native request schemas, which is a schema-lookup hint rather than guidance on when to reach for this tool. There is no statement of when to use this versus get_support_incidents (list) or get_support_incidents_history, and no preconditions such as needing a known incident id.

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