delete_reading_annotation

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

The description warns 'Changes stored DeepTutor learning data', which is an accurate behavioral disclosure for a delete operation. However, the annotation destructiveHint is set to false, directly contradicting the notion that this tool modifies stored data. This contradiction is a serious inconsistency: the agent cannot trust the annotation, and the description's warning conflicts with the structured metadata. Per the rubric, a contradiction yields a score of 1.

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 two sentences with no fluff. The warning is front-loaded, immediately signaling importance, and the action statement follows. Every word earns its place. It is concise while conveying the critical usage warning.

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 simple delete tool with an output schema, the description covers the essential context: it warns about data changes and the explicit-request requirement. It does not discuss error handling or idempotency, but those are minor given the straightforward action and the presence of an output schema. However, the annotation contradiction reduces the overall completeness, as structured metadata is unreliable.

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 100%, and each parameter (material_id, annotation_id, confirm) is already described in the schema, including the confirm boolean's purpose ('Set true when this write is authorized by the current user request'). The description does not add any new semantic information beyond the schema, so the baseline of 3 applies.

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: 'Delete one reading annotation' – a specific verb and resource. It distinguishes from siblings like save_reading_annotation and list_reading_annotations by explicitly saying 'delete' and 'one reading annotation'. The warning at the start reinforces the specific nature of the operation.

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 explicitly states when to call: 'call only when the learner explicitly requests this action'. This is a strong usage condition. It also advises to 'Check the target ID and values', which guides the agent on pre-call verification. Although it does not name an alternative, the condition is unambiguous and sufficient for an agent to decide when to invoke the tool.

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