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

Annotations only indicate readOnly=false and idempotent=true; the description adds far more: deprecation status, idempotent retry semantics, required scopes, agent-scoped bearer key restrictions, and the limitation that reports do not approve or complete facility handling. This is substantial behavioral context beyond what structured fields provide, and it does not contradict the annotations.

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 a dense wall of text with redundancy: the required scopes are stated twice. The sentence about rollout switches, member approval, assignment, credential environment, and SQL authorization is opaque and does little to help an agent invoke the tool. The deprecation notice is well front-loaded, but overall structure and brevity are weak.

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?

Given the tool's complexity, the description covers deprecation, authentication scopes, idempotency retry behavior, and important limitations. The output schema presumably covers return values, so the absence of response details is acceptable. The main gaps are clarifying item_id semantics and trimming confusing cross-references to REST authorization details, but the definition is still largely sufficient.

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 0% schema description coverage, the description compensates by explaining that context_version must be the exact fetched value, run_id must be non-sensitive, and retries must reuse the same idempotency_key and request. It does not explicitly define item_id, though the endpoint path's :id hints at its role, so the parameter semantics are mostly but not fully clarified.

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?

Clearly states a specific verb and resource: report actual external-worker processing through /v1/agent-inbox/:id/acknowledgments. It also draws a boundary by saying reports cannot approve or complete facility handling, which helps distinguish it from related inbox actions. The deprecated/no-successor note is upfront and adds clarity rather than obscuring purpose.

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?

Gives concrete use instructions: send exact fetched context_version, outcome, and non-sensitive run_id, and retry only with the same idempotency_key and request. It also provides exclusions: never report work before doing it and reports cannot approve or complete facility handling. No alternative tool is named, but that is expected since the description explicitly states there is no successor.

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