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

Annotations already mark this as non-read-only and idempotent. The description adds context about key-value scoping by identifier, 24-hour retention for anonymous sessions, persistent memory for authenticated users, and the ability to delete via forget. No contradiction with 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?

The description is five sentences, all purposeful, with the first sentence front-loading the purpose. It includes examples and persistence details, but each clause earns its place without 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 key-value write with two fully described parameters, the description covers discovery triggers, retention policy, and lifecycle pairing. No output schema exists, but return value is not critical for deciding when to use this tool.

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 covers both key and value with examples at 100% coverage, so the baseline of 3 applies. The description repeats the key-value concept but does not add new parameter-level detail beyond the schema.

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 opens with 'Save data the agent will need to reuse later,' clearly stating a specific verb and resource. It also distinguishes the tool from siblings recall and forget by explicitly pairing with them for retrieval and deletion.

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 'Use when you discover something worth carrying forward' and explains the benefit of avoiding future lookups. It also names recall and forget as complementary tools and clarifies persistence differences for authenticated vs anonymous sessions.

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