Confirm a memory is still accurate

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

Annotations only declare the safety profile (readOnly=false, destructive=false, idempotent=false); the description goes well beyond that by stating exactly what mutates (updated time, history entry), what does not (stored value), the write cost, and two concrete error codes with their trigger conditions. That is precisely the extra behavioral context annotations cannot convey.

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?

Front-loaded with the core action in the first sentence, followed by only the details an agent needs: mutation semantics, cost, and failure modes. No repetition of the title or schema, and 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 mutation tool with an output schema present, the description covers behavior, side effects, and error conditions thoroughly enough to call it safely. The remaining gap is the unexplained reason and idempotency_key parameters, which neither the schema nor the description defines.

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% across 4 parameters, so the description must carry the burden. It explains expected_version well (an optimistic-concurrency check that yields version_conflict), but says nothing about key, reason, or idempotency_key — notably that idempotency_key is the dedupe mechanism even though annotations declare idempotentHint=false. Partial compensation only.

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 states a specific verb+resource (record that a memory is still accurate) and immediately clarifies the key distinction from a value-changing edit: 'The stored value is not changed.' That implicitly separates it from siblings like revise and rollback. It never names a sibling explicitly, so it falls just short of the top band.

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?

Usage is implied by 'Record that an existing memory is still accurate,' and the failure modes give implicit preconditions (the key must exist, and expected_version must match). However, there is no explicit when-to-use/when-not guidance or named alternative (e.g., revise when the value actually changed), leaving the routing decision to inference.

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