Retract Annotation

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 covers the mutation (soft-delete with retracted_at), irreversibility from the agent's side, external visibility, destructive classification, human approval requirement, and dry-run capability. This is comprehensive for a destructive mutation tool.

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 tightly packed paragraphs. The first sentence delivers the core purpose, the second conveys consequences and requirements. No filler or redundancy; every sentence earns its place.

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 3-parameter mutation tool with no output schema and no annotations, the description covers the essential runtime context: what the operation does, its safety implications, how to preview it, and what credential is needed. Nothing critical is missing for an agent to call it correctly.

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. It explains dry_run (preview without committing) and approval_token (human-supplied requirement). annotation_id's purpose is obvious from the tool's name and the sentence 'Soft-delete an annotation', so it is adequately covered.

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 opens with a specific verb and resource: 'Soft-delete an annotation (sets retracted_at)'. This clearly identifies the operation and its mechanism, and distinguishes it from sibling tools like annotate_metric (which creates) and list_annotations (which reads).

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 important context: it is destructive, requires human approval, and supports dry_run preview. However, it never explicitly states when to use this tool versus alternatives, such as 'use this to undo an annotation created with annotate_metric'. The usage conditions are implied rather than spelled out.

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