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

Annotations already indicate a write operation (readOnlyHint=false) and safe repetition (idempotentHint=true). The description adds persistence details: identifier scoping, 24-hour retention for anonymous sessions, and persistent memory for authenticated users. It does not list failure modes or overwrite behavior, but the additional context is beyond 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?

Five sentences, each providing distinct value: action, use-case, storage format, persistence policy, and sibling relationships. No redundant phrases.

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?

Covers purpose, when to use, storage mechanics, retention, and integration with recall/forget. No output schema is defined, so no return-value explanation is required. Simple two-string tool is fully addressed.

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?

Schema covers 100% of parameters with detailed descriptions and examples. The tool description adds general usage context but no new parameter-specific semantics; the baseline of 3 applies.

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 the verb 'save' with a clear object ('data the agent will need to reuse later') and explicitly names sibling tools 'recall' and 'forget' to differentiate retrieval and deletion. This distinguishes it from the 30+ sibling tools.

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 states when to use ('when you discover something worth carrying forward'), provides concrete examples, and says 'Pair with recall to retrieve later, forget to delete,' explicitly mapping alternatives. This goes beyond implied usage into explicit exclusions.

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