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

Annotations already declare readOnly and idempotent behavior. The description adds valuable context about scoping ('Scoped to your identifier (anonymous IP, BYO key hash, or account ID)') and the dual behavior of retrieving a single key versus listing all keys. This goes beyond annotation basics, though it could mention error handling for missing keys.

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 two tight sentences, front-loaded with the core action. Every phrase earns its place: the retrieve/list distinction, usage guidance, scoping, and sibling references. No fluff or 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 tool with a single optional parameter, no output schema, and clear annotations, this description is remarkably complete. It covers purpose, modes of operation, scoping, and how it relates to remember and forget. Nothing essential is missing for an agent to invoke it correctly.

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 already documents the 'key' parameter well (100% coverage). The description adds real meaning by giving concrete examples of key values (target ticker, address, prior research notes) and reinforcing the conceptual meaning of omitting the key. This enriches the schema's formal definition.

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 states the tool's function: 'Retrieve a value previously saved via remember, or list all saved keys (omit the key argument)'. It uses specific verbs and resources, and explicitly contrasts with sibling tools 'remember' and 'forget', making its purpose unmistakable.

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 says 'Use to look up context the agent stored earlier — without re-deriving it from scratch', establishing when to use recall. It also explicitly guides pairing: 'Pair with remember to save, forget to delete', clarifying alternatives and exclusions.

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