value_retract

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states that this is a non-destructive operation ('this is not a delete') and explains what happens: the retraction timestamp and reason are recorded, and history is preserved. This gives the agent confidence in the tool's side effects.

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 three sentences long, with the key action in the first sentence and the history preservation and sibling differentiation in the second and third. It is front-loaded and every sentence adds value. One point deducted for minor redundancy: 'the history of what was held and when is preserved' is slightly verbose but still useful.

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 complexity of the tool (2 params, 1 required, simple types, output schema present), the description covers all essential aspects: purpose, side effects, non-destructive nature, and relationship to siblings. The output schema can explain the return format, so the description's lack of return value detail is acceptable. The tool is fully described for an agent.

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 description coverage is 0%, so the description must compensate for parameter meaning. It does so effectively for the context: 'cause' is implied by 'retract a value with cause' (optional reason for retraction) and 'value_id' is implied as the target. While not a detailed parameter listing, the functional description is sufficient for an agent to infer usage. One point deducted for not explicitly naming both parameters in context.

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 action ('Retract a value with cause'), the resource ('value'), and the effect ('Records the retraction timestamp and reason'). It also distinguishes itself from siblings by noting it preserves history and is not a delete, and explicitly names the alternative 'value_drop' for permanent deletion.

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?

The description provides explicit guidance on when to use this tool ('to retract with cause') and when not to ('use value_drop for permanent deletion'), directly differentiating from a sibling tool. This helps an agent decide between value_retract and value_drop.

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