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

The description adds significant context beyond the annotations: persistence across sessions and API-key rotation, the fact that SeaWeb's credential filter is a backstop rather than a guarantee, and that unlabelled secrets will be stored as written. This is exactly the behavioral nuance an agent needs when deciding whether to call this write tool.

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 front-loaded with the core purpose, followed by concrete examples and then a necessary security warning. Every sentence earns its place; there is no filler or repetition of schema information.

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 two-parameter write tool with no output schema, the description covers what the tool does, when to use it, what not to store, and the real-world risk of the credential filter. The agent has everything needed to invoke it correctly and safely.

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?

With schema description coverage at 0%, the description carries the burden of explaining the parameters. The examples like remember('dietary', 'vegan') and remember('party_size', '2') clearly show that key is a semantic label and value is the stored preference. It could be even more explicit about key uniqueness or value formatting, but the examples sufficiently bridge the schema gap.

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 states a specific verb and resource: 'Save a durable preference on YOUR agent profile', and clarifies that this is account-level memory surviving sessions and API-key rotation. The examples ('dietary', 'home_neighborhood', 'party_size') make the intended use unmistakable and distinguish it from sibling tools like recall and log_outcome.

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 says 'Use for defaults worth reusing' and gives concrete examples. It also gives a strong when-not: never store passwords, session cookies, or credentials. However, it does not explicitly name an alternative tool for storing credentials or for non-durable state, so the guidance falls just short of fully routing the agent to alternatives.

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