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

The description explicitly calls the operation 'read-only' and says it does not execute changes, while annotations declare readOnlyHint=false and destructiveHint=true. This directly contradicts the structured safety profile an agent relies on, and no other behavioral details (state touched, side effects, retry behavior) are offered.

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?

Three short sentences, front-loaded with purpose followed by prerequisites and exclusions; no filler. The mild cost is that sentence one duplicates the title rather than extending it.

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 six-parameter tool with an idempotency key, an optimistic-concurrency expected_version, and no output schema, the description leaves the mechanics of the call entirely to the schema. Combined with the read-only framing against destructive annotations, an agent cannot form a correct expectation of what the call does.

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?

Six parameters with only 67% schema description coverage, and the description names none of them. 'Authorized sample case' obliquely gestures at case_id and 'current runtime access' vaguely at expected_version, but capability, company, environment, and idempotency_key get no added meaning anywhere in the prose.

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 first sentence states a concrete verb and resource (request a capability test) scoped to an authorized sample case, which distinguishes it from sibling capability_checks_get/list/report/save. It is, however, an almost verbatim restatement of the title, so it adds little beyond what the title already conveys.

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?

It gives a prerequisite-binding hint ('needs investigations.request and current runtime access') and a boundary ('does not approve or execute customer changes'), which is implicit when-not guidance. It never routes the agent between this tool and siblings like summer_verification_run, summer_actions_prepare, or summer_capability_checks_report.

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