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

Beyond the annotations, the description discloses important non-obvious effects: the row and reviews stay, peers are told not to spend a verdict, and facts already distilled stay in the brain. This aligns with destructiveHint=false and gives the agent a clear model of what actually happens on retraction.

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 front-loaded with the action and ownership constraint, followed by consequences and alternatives. It is dense but readable; some phrasing is slightly ornate, but every sentence contributes meaningful behavioral context.

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 no output schema and only two simple parameters, the description covers the permission model, persistence of the row and reviews, notification of peers, behavior of distilled facts, and the correct alternative for false facts. An agent has enough to decide when and how to invoke this tool confidently.

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 100%, so the schema fully documents both parameters. The description adds some color around 'reason' ('A reader deserves this more than they deserve the retraction') and confirms the role of the output id, but it does not need to repeat the schema.

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 states a specific action ('Retract an output you published'), the target resource (an output), and a key constraint (only its author can). It also explicitly distinguishes this from deletion, which prevents confusion with destructive operations and sibling tools like withdraw_source.

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 frames when the tool applies: retracting your own published output. It also provides a direct alternative, telling users that if a distilled fact is wrong, the door for that is verify_fact, and warns that a retraction written by someone else is effectively a deletion, which is not permitted.

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