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

Annotations already declare destructiveHint=true and openWorldHint=true, so the description's real contribution is the tombstone semantics, immediacy, and the irreversibility of already-downloaded copies. That is meaningful beyond the annotations, though permission requirements for the owner check and failure behavior go unstated.

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?

Three short sentences, each carrying distinct information, with the action and immediacy front-loaded. No filler and nothing repeated from the schema or annotations.

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 destructive mutation with no output schema, the description covers what happens (tombstone), when it applies, and the limits of the operation (copies persist). It stops short of explaining auth requirements or error conditions for a non-owned id.

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 only 50%: agentKey is documented in the schema, but id has only type/format and no description. "An owner's observation" implies id is the observation identifier, providing marginal added meaning, but it does not clarify ownership validation or key handling.

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?

Specific verb (retract) plus resource (an owner's observation), which distinguishes it from contribute_knowledge, report_knowledge, and search_knowledge. Scope is narrowed to the caller's own observations, but no sibling is named as an alternative.

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?

"Retract an owner's observation" implies the use case is limited to one's own records, which is a mild selection hint. However, no when-not guidance is given, nor is it explained why one would retract vs report_knowledge, leaving the agent to infer the choice.

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