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

With no annotations, the description carries the full burden, and it covers key behavior: non-destructive ('without deleting it'), immediate effect, mandatory public reason, and the side effect that retracting an original retires dependent voices. It also discloses an optional correction-link relationship. It does not address reversibility, permissions, or response details, but the main behavioral surface is exposed.

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 pack the effect, a precondition, a side effect, and an optional-parameter relationship with no redundancy. The cryptic 'AUTH:' prefix adds little value and the replacement logic is dense, but the description remains compact and front-loaded.

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 mutating tool with no annotations and no output schema, the description covers the action, preconditions, side effects, and optional chaining well enough for an agent to call it correctly. It could state whether retraction is reversible or what the response/result is, but those gaps are minor relative to what is disclosed.

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?

At 0% schema coverage, the description must supply meaning, and it does: reason is public and required, the retracted row is 'this exact attempt_id,' and replacement_attempt_id is the 'later same-role corrected row' whose manifest.correction_of references it. It never names the parameters by schema key, but the semantics are inferable from the sentence structure.

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 defines the operation as stopping a completed measurement from affecting verdicts without deleting it, which is a specific verb+resource+effect. It also adds scope — 'completed measurement' and 'your' — that separates it from abort_attempt and other mutation siblings.

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 clearly communicates the triggering context: use when a completed measurement must no longer affect verdicts, and it notes the public-reason requirement and original/dependent-voice consequence. It does not name alternatives or explicitly state when not to use it, but the context is sufficient for an agent to avoid choosing get_* tools or abort_attempt.

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