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

The annotations already mark the tool as idempotent and non-destructive, and the description adds valuable behavioral context beyond these: key-value storage, scoping by identifier, and the difference between authenticated users (persistent memory) and anonymous sessions (24-hour retention). This helps the agent anticipate data persistence behavior without contradicting any annotation.

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 front-loaded with the core action, then provides usage guidance, storage model, and companion tools—all in five compact sentences. Every sentence contributes meaning, and the examples are illustrative without unnecessary filler. It is appropriately sized for a simple two-parameter tool.

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 key-value memory tool with no output schema, the description fully covers the value proposition, when to use it, persistence semantics, authentication differences, and related tools. It gives an agent everything needed to decide when and how to invoke it, with no critical gaps.

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 documents both parameters (key and value) with examples and descriptions, so the description need not repeat them. The description adds general context about the key-value structure but does not enhance parameter-level detail beyond what the schema provides. Baseline 3 is appropriate given 100% schema description 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 clearly states the tool's purpose: 'Save data the agent will need to reuse later — across this conversation or across sessions.' It identifies the action (save), resource (key-value data), and scope, and distinguishes itself from sibling tools by explicitly pairing with 'recall to retrieve later, forget to delete.' Examples of what to store (resolved ticker, target address, user preference) further clarify intent.

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 explicitly says when to use the tool ('Use when you discover something worth carrying forward'), providing concrete example use cases. It names companion tools (recall and forget) for retrieval and deletion, but does not give explicit 'when not to use' guidance or contrast with other storage/search tools. This is clear context but not exhaustive exclusion.

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