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

The description discloses that the entry is immutable and replacement requires its own promotion, which adds context beyond annotations. It also mentions preserving history, contradicting any expectation of deletion. However, it doesn't detail what 'retire' does to linked answers or what the response looks like. Given annotations already indicate destructive and open-world hints, this is adequate but not comprehensive.

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, each adding value: the action, the permission requirement, and the replacement process. It is front-loaded with the core action and covers essential points without redundancy. Could be slightly more structured with bullet points, but it's appropriately concise.

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 is complex (5 params, no output schema, annotations only partially specify behavior), the description covers the main intent, permission, and process but omits details like how to handle failure or what happens to linked answers. It doesn't state return values, but without an output schema that's not critical. It's sufficient for an agent to attempt a call but lacks edge case guidance.

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 coverage is 40%, meaning some parameters (projectId, idempotencyKey) have descriptions in the schema. The description doesn't add parameter-specific details beyond what the schema provides, such as the meaning of revision or the exact format of entryId. It expects the agent to rely on the schema for those, which is acceptable as per baseline 3 given partial coverage.

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 the verb 'Retire' and the resource 'the exact reusable answer', indicating this tool retires a specific library entry. It distinguishes it from related tools like reuse_library_entry and propose_library_entry by emphasizing retirement and the need for reviewer rights. However, it doesn't explicitly name sibling alternatives, so it's not a 5.

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 specifies the requirement of reviewer rights and implies the context of retiring an entry, which helps decide when to use it. It also hints that a replacement needs new promotion, but it doesn't explicitly say when not to use it or mention alternatives like retire_business_claim. Overall, it provides clear context but lacks explicit exclusions.

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