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

Annotations already cover the safety profile (readOnly=false, destructive=false, idempotent=true), and the description adds context they cannot express: secrets must not be stored, and a blocked write must not be treated as success. The retry contract around operation_id is also operational guidance rather than annotation restatement.

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, front-loaded sentences with no filler. 'A blocked write is not success' is terse to the point of being slightly cryptic, but nothing is wasted.

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?

No output schema and low parameter coverage, so the description carries more weight than it does. It covers safety and retry behavior well but leaves durability selection and the meaning of 'about' unexplained, which an agent needs to call this 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 coverage is 25% – only operation_id is documented in the schema, and the description merely reinforces that. The two most ambiguous parameters, 'about' (what is it the subject?) and 'durability' (durable vs time_bounded vs transient), get no explanation in either place, so the description does not compensate for the coverage gap.

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: store information the user intends to remember. The phrase 'intends to remember' implicitly separates it from the capture/import siblings, though no sibling is named 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?

Provides one hard exclusion ('Do not store secrets') and retry guidance tied to operation_id, which is genuinely useful. It never routes the agent to alternatives (memory_search before storing, memory_forget, the capture tools), so the use-vs-sibling decision is left to inference.

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