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

Annotations already declare the tool as non-destructive, idempotent, and non-read-only. The description adds valuable behavioral context beyond this: key-value scoping by identifier, persistence differences between authenticated (persistent) and anonymous (24-hour) sessions, and the ability to span conversations/sessions. This enhances the agent's understanding without contradicting 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?

Three concise sentences: first states the primary purpose, second gives actionable usage examples, third covers storage details and companion tools. Information is front-loaded, with no redundancy or filler. Each sentence earns its place.

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?

The description is complete for this simple write tool: purpose, usage, scoping, persistence, and relationship to siblings are all covered. With a fully documented schema and no output schema, there is no missing critical information. It adequately equips the agent to select and invoke the tool.

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 schema covers both parameters with descriptive examples (key and value), so the description need not repeat them. The phrase 'key-value pair scoped by your identifier' adds slight semantic context about the key's scoping, but overall the description offers minimal additive parameter detail. Baseline 3 is appropriate given full 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 verb and resource ('Save data the agent will need to reuse later') and clarifies the key-value store nature. It distinguishes itself from siblings by explicitly pairing with 'recall' and 'forget', which are close alternatives, making its role 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?

Provides explicit when-to-use guidance with concrete examples ('a resolved ticker, a target address, a user preference, a research subject'). It also tells the agent when to use companion tools ('Pair with recall to retrieve later, forget to delete'), effectively covering both use and non-use cases.

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