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

Annotations already declare non-read-only, idempotent, and non-destructive. The description adds meaningful context: key-value scope by identifier, persistent memory for authenticated users vs. 24-hour retention for anonymous sessions, and pairing behavior with recall/forget.

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?

Four sentences with no wasted words. Purpose, usage, storage semantics, and related tools are all covered efficiently and front-loaded.

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 2-param tool with full schema coverage and annotations, the description is complete. It explains persistence, scoping, and integration with sibling tools. No output schema is needed for this straightforward write operation.

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 covers both parameters with descriptions (key as memory key, value as text). The description provides illustrative examples for key (e.g., 'subject_property') and notes free-form nature of value, but this is largely redundant with schema. 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 uses a specific verb and resource: 'Save data the agent will need to reuse later.' It clearly distinguishes from siblings by explicitly mentioning recall (retrieve) and forget (delete) as complements.

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 an explicit 'Use when' condition ('when you discover something worth carrying forward... so you don't have to look it up again') and names alternative tools (recall, forget) with their distinct roles.

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