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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered; the description still adds real value with authorization scopes, a privacy note ('private review'), the explicit 'No write or customer action', and the reservation-adapter scope limit. It does not explain what makes a case 'eligible' or how test evidence is shaped, which are the remaining behavioral unknowns.

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?

Six short sentences, front-loaded with the core action and return payload, with constraints following in decreasing importance. A few clauses are jargon-heavy ('reservation adapter', 'Policies and Operations write authority') but each still carries actionable information rather than restating the name.

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?

There is no output schema, so the description compensates by enumerating return fields, and for a single-parameter read tool it covers authorization, scope limits and side-effect posture. The main gap is that 'eligibility' and 'existing test evidence' remain undefined concepts, so an agent knows what fields exist but not what they mean.

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 one parameter and 0% schema description coverage, the description carries the burden: 'Accepts its ID or reference' does add meaning beyond the bare 'caseId' string. However, it never reconciles 'reference' with the schema's caseId field, nor does it state whether a reference must be resolved first, so the extra semantics are suggestive rather than precise.

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 uses a specific verb and resource — 'Read one exact existing case' — and states the output it returns (canonical caseId, revision, eligibility, existing test evidence). It implies the boundary against the sibling 'mark_case_as_test' by framing this as the pre-read before 'an explicitly requested test classification' and disclaiming 'not a universal lifecycle classifier', though it never names the sibling outright.

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 says when to use it ('before an explicitly requested test classification') and gives a real exclusion ('supports uncommitted cases only; this is not a universal lifecycle classifier'). Access prerequisites (Owner with Policies and Operations write authority, policy:read/write and operations:read consent) are stated, but the intended alternative when the case is committed or the caller lacks that authority is left unspecified.

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