knowledge_retract

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

Goes beyond annotations by clarifying the non-destructive nature (hidden but still retrievable via kb_at), the required role, and the need for mapped tags. This is genuinely useful behavioral detail.

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?

Two snappy sentences, front-loaded with the key concept. Slightly dense but no filler.

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?

Covers the essential semantics for a flat-parameter tool, but the return value is not described (e.g., confirms retraction or returns the tombstone). Minor gap only.

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?

With 0% schema coverage, the description flags reason as required and implies the role/tag requirement, but doesn't define what kind of reason is expected. Partial help for the agent.

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 a specific verb ('tombstone') and its effect: the atom is hidden from default search but remains fetchable by ID. This unambiguously distinguishes it from a hard delete.

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?

No explicit guidance on when to retract instead of delete or flag, nor when not to use it. The description explains the behavior but doesn't route the agent toward the right choice among sibling mutating tools.

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