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

The description adds valuable behavioral context beyond the annotations: persistence semantics ('Authenticated users get persistent memory; anonymous sessions retain memory for 24 hours') and scoping by identifier. It does not contradict any annotation; idempotentHint and readOnlyHint align with the write-and-overwrite nature of saving key-value pairs.

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 three concise sentences, front-loaded with the core purpose ('Save data the agent will need to reuse later'). Every sentence adds distinct value: what to save, when to use it, persistence behavior, and companion tools. No filler or redundancy.

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, the description fully covers the essential context: purpose, usage triggers, persistence behavior, and related tools. The annotations cover idempotency and non-destructiveness, so the description does not need to repeat those. It is sufficiently complete for an agent to invoke it 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 already provides 100% description coverage for both parameters ('key' and 'value') with examples. The description adds minimal new parameter-specific detail, only noting the key-value pair structure and identifier scoping, which is more of a behavioral note than parameter semantics. The description does not compensate enough to exceed 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 uses a specific verb ('Save data') and a clear resource ('data the agent will need to reuse later'), and it differentiates itself from sibling tools by explicitly mentioning 'recall' and 'forget' for retrieval and deletion. The phrase 'across this conversation or across sessions' clarifies the scope of what is stored.

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?

It provides explicit when-to-use guidance with concrete examples ('a resolved ticker, a target address, a user preference, a research subject') and explains the benefit ('so you don't have to look it up again'). It also names companion tools ('Pair with recall to retrieve later, forget to delete'), giving clear alternatives for the same workflow.

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