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

Annotations already convey safety (readOnly=false, destructive=false, idempotent=true). The description adds meaningful behavioral context beyond annotations: 'Stored as a key-value pair scoped by your identifier,' 'Authenticated users get persistent memory; anonymous sessions retain memory for 24 hours.' This discloses persistence semantics, scope, and TTL—valuable for the agent. It does not explicitly state overwrite behavior, but the idempotentHint covers that already. No contradiction.

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?

The description is compact and front-loaded, opening with the primary action. It uses four sentences, each serving a purpose: purpose, when to use, storage/scope details, and companion tools. It is slightly longer than the minimum but contains no fluff, earning a 4.

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 simple key-value write tool with no output schema, the description is remarkably complete. It covers what to store, when to use it, persistence behavior, session-specific TTL, scoping by identifier, and how it relates to recall/forget. An agent has sufficient context to invoke the tool correctly without ambiguity.

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?

Input schema covers 100% of parameters with clear descriptions, so the baseline is 3. The description adds some usage examples (e.g., 'resolved ticker, target address, user preference') that help illustrate appropriate key/value content, but it does not materially expand on the schema-provided semantics. Therefore, the score remains at the baseline.

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 the tool's purpose: 'Save data the agent will need to reuse later' with a specific verb ('save'), resource ('data'), and scope ('across this conversation or across sessions'). It also distinguishes from siblings by explicitly naming companion tools 'recall' and 'forget' and providing concrete examples (resolved ticker, target address, user preference).

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?

The description provides explicit when-to-use guidance: 'Use when you discover something worth carrying forward' and explains the benefit ('so you don't have to look it up again'). It also mentions alternatives by pairing with 'recall to retrieve later, forget to delete.' However, it lacks an explicit when-not-to-use statement, so it falls just short of a 5.

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