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

Beyond annotations (which indicate idempotent and non-destructive behavior), the description adds critical context: key-value pairing, scoping by identifier, and session-dependent persistence (24h for anonymous, permanent for authenticated). This is valuable behavioral information not present in the annotations.

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 a compact set of four sentences, front-loaded with the core action. Each sentence adds necessary context: usage trigger, storage format, persistence behavior, and sibling tool relationships. No extraneous words or filler.

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?

Given the simple nature of a store tool, the description covers the essential aspects: what to store, when to use it, scoping, persistence, and how to retrieve/delete later. The parameters are fully documented in the schema, annotations cover safety/idempotency, and no output schema is needed for a basic save operation. The description is complete for an agent to invoke 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?

The input schema fully describes both parameters (key and value) with examples, achieving 100% schema description coverage. The description echoes these examples but adds no new parameter-level syntax or constraints. It does mention 'any text' for value, but that's already in the schema, so it merely reinforces rather than extends.

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 begins with a specific verb and resource: 'Save data the agent will need to reuse later,' clearly stating the tool's function. It further specifies usage with examples (resolved ticker, target address, user preference) and distinguishes itself from siblings by explicitly mentioning 'Pair with recall to retrieve later, forget to delete.'

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.' It also clarifies exclusions/alternatives by naming sibling tools recall and forget, and notes the persistence difference between authenticated and anonymous sessions, giving the agent a clear decision framework.

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