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

Beyond annotations (idempotentHint=true, readOnlyHint=false), the description reveals key behavioral traits: persistence across sessions/API-key rotation, account-level scoping, and the security caveat that SeaWeb's credential filter is a backstop, not a guarantee. The warning 'an unlabelled secret in a free-text value will be stored as written' is critical transparency. 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 somewhat long but every sentence earns its place: purpose, examples, exclusion of credentials, and a security caveat. It is front-loaded with the core purpose and then builds context. Could trim slightly but is well-structured and readable.

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-parameter write tool with no output schema, the description is highly complete. It covers persistence, usage, exclusions, and security behavior. It doesn't mention overwrite semantics, but idempotentHint already implies that. Given the sibling 'recall' handles retrieval, this fully covers the write side.

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 schema provides only key/value strings with no descriptions (coverage 0%), but the description compensates with examples that clarify key as a short identifier and value as a preference. It also explicitly says what values should NOT be (credentials), adding semantic guidance beyond the raw schema. It does not give naming conventions or length limits, so not a 5.

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 a specific verb+resource: 'Save a durable preference on YOUR agent profile'. It clearly distinguishes this tool from siblings like 'recall' by emphasizing persistent account-level memory. The examples ('remember("dietary", "vegan")') further cement the intended use.

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 explicitly says when to use: 'Use for defaults worth reusing' and provides three concrete examples. It also gives a clear when-not: 'Never store passwords, session cookies, or other credentials here' and states memory is for preferences, not login state. However, it does not name alternative tools (e.g., 'recall' for retrieval), so it lacks explicit alternative recommendations.

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