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

Annotations already signal mutation, destructiveness, idempotency, and open-world behavior. The description adds useful context about requiring an existing actor-bound promotion and current evidence, and clarifies that no new approval is inferred. However, it does not disclose what the destructive application actually changes or overwrites, which is a meaningful gap given destructiveHint=true.

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 sentences, no filler, with the core recovery scenario front-loaded. Each sentence adds distinct value: when to use, required identifiers/state, and a safety caution about checking for prior success.

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?

The description is nearly complete for a retry/recovery operation: it names the triggering condition, required inputs, prerequisites, and a key ambiguity to check before invoking. It could go further by describing what the agent should expect on success or conflict, but with no output schema and annotations already covering mutation/idempotency, the missing detail is not critical.

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 only 40% schema description coverage, the description compensates for the two most recovery-critical parameters: confirmationId is explained as the challenge ID, and revision is explained as the original exact revision. The other parameters are either already described in the schema (projectId, idempotencyKey) or reasonably self-evident from the field name (entryId), though entryId lacks explicit elaboration.

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 clearly states a specific recovery scenario: resuming a library promotion after a human confirmation succeeded but the application was interrupted. It distinguishes this tool from confirmation and request tools by anchoring it to the 'apply after confirmation' stage and using precise recovery language.

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 explicitly says when to use the tool (recovery after interrupted application) and gives a strong prerequisite: use the confirmation challenge ID and original revision, and inspect the entry first if application may already have succeeded. It does not name sibling tools explicitly, but the when/when-not conditions are clear enough to route an agent correctly.

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