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

The description adds useful behavioral context beyond annotations: it explains memory persistence (24 hours for anonymous, persistent for authenticated), scoping by identifier, and the key-value storage model. Annotations already indicate idempotent and non-destructive, which the description does not contradict.

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 concise (three sentences) and well-structured. It starts with the core purpose, then provides usage guidance, and ends with pairing with other tools. Every sentence adds value without repetition.

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 covers all essential aspects: purpose, when to use, data persistence, scope, and integration with recall and forget. For a simple key-value store with no output schema, it provides sufficient context for correct tool usage.

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 has 100% coverage with descriptions for both 'key' and 'value'. The description adds context about usage (e.g., naming conventions for keys) but does not significantly extend the schema's explanation beyond examples. Baseline score of 3 is appropriate.

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 defines the tool's purpose: saving data for reuse across conversations or sessions. It uses specific verbs ('save', 'reuse') and distinguishes from sibling tools like recall and forget by explaining the pairing.

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 states when to use the tool ('when you discover something worth carrying forward'), provides examples of data to save, and mentions alternatives (recall, forget). It also clarifies scope and persistence differences between authenticated and anonymous sessions.

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