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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is known. The description adds real value by explaining what 'destructive' actually means here — recall is suppressed while audit history is retained — which prevents an agent from assuming irrecoverable data loss. It also adds retry semantics, though those partly overlap the idempotentHint annotation.

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, front-loaded with the use condition, then behavior, then the retry contract. No filler and nothing redundant in ordering.

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 does well on semantics and safety but leaves gaps around the handle format and what 'reason' is for. An agent could invoke it correctly but may guess at argument content that the schema does not explain.

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 33%: operation_id is documented in the schema itself, and the description's 'Use operation_id for safe retries' largely repeats that. The two remaining parameters get no help — the handle's required '^[mp]:[0-9a-f]{8,64}$' format and the purpose of 'reason' are never explained in prose, leaving the low coverage uncompensated.

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?

States a specific verb and resource ('Invalidate a memory') and immediately bounds the scope with 'only when the user intends to forget it'. It also disambiguates from a related-but-different operation by saying it is 'not physical deletion', which separates it from a hard-delete sibling without naming one explicitly.

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?

Gives a clear precondition for use (the user actually intends to forget) and an implicit exclusion (do not use for physical erasure). It does not name a concrete alternative tool such as memory_remember for the opposite direction, so the routing guidance is clear but not exhaustive.

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