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

Annotations already declare the write semantics (readOnlyHint=false), idempotency, and non-destructiveness. The description adds genuinely new behavioral context beyond those annotations: the key-value store is 'scoped by your identifier' and retention is auth-dependent — persistent for authenticated users versus 24 hours for anonymous sessions. No contradiction with 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?

Five sentences, each carrying distinct information: purpose, when-to-use triggers, storage model, retention policy, and sibling routing. The opening is front-loaded with the verb and resource, though the final pairing clause ('forget to delete') reads slightly ambiguously despite the sibling literally being named 'forget'.

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 two-parameter tool with strong annotations and 100% schema coverage, the description covers purpose, usage triggers, memory scoping, and retention semantics. The only notable omission is any statement of the return value or confirmation behavior, which is minor given the absence of an output schema.

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 100%, with both key and value fully described in the input schema including format examples. The description reinforces the key-value storage model but adds no parameter-level detail beyond what the schema already provides, so the baseline 3 applies.

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 opens with a specific verb and resource — 'Save data the agent will need to reuse later' — and explicitly names the sibling operations ('Pair with recall to retrieve later, forget to delete'), so an agent can distinguish it from recall and forget without opening their schemas. Concrete examples (resolved ticker, target address, user preference, research subject) make the tool's job unmistakable.

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 gives an explicit trigger condition — 'Use when you discover something worth carrying forward' — with concrete examples of what qualifies and the motivating rationale ('so you don't have to look it up again'). It routes to the related siblings (recall for retrieval, forget for deletion), though it stops short of stating explicit when-not conditions, leaving exclusion largely to inference.

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