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

The description goes well beyond the provided annotations by disclosing the storage as key-value pairs scoped by the agent's identifier, persistence for authenticated users, and a 24-hour retention window for anonymous sessions. This adds meaningful behavioral context that annotations alone do not convey, and nothing contradicts the readOnly/idempotent/destructive hints.

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 efficiently structured with a front-loaded purpose, followed by use-case examples, storage semantics, retention behavior, and related tools. Each of the five sentences contributes unique information without redundancy 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?

For a simple two-parameter tool with no output schema and good annotations, this description covers purpose, when to use, storage scope, persistence behavior, and how to retrieve or delete later. It provides sufficient context for reliable invocation, and the only minor question about overwriting is reasonably implied by 'save' and idempotentHint.

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 already provides full descriptions and examples for both key and value, covering 100% of parameters. The description only refers generically to a 'key-value pair' and does not add additional parameter-level detail, so it sits at the baseline for high schema coverage.

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 action and resource: 'Save data the agent will need to reuse later,' spanning conversation and cross-session persistence. It clearly differentiates itself from sibling tools recall and forget by framing this as the storage operation, with retrieval and deletion explicitly assigned to those siblings.

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?

Explicitly instructs when to use: 'Use when you discover something worth carrying forward,' with concrete examples like resolved tickers and user preferences. It also gives direction for companion tools: 'Pair with recall to retrieve later, forget to delete,' effectively describing the usage context relative to alternatives.

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