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

Annotations already confirm read-only and non-destructive behavior. The description adds scoping details (anonymous IP, BYO key hash, account ID) and the dual behavior of returning a single value or all keys, which annotations do not convey.

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?

Three sentences, front-loaded with the primary function, followed by use cases and scoping/pairing. No redundant wording or filler.

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?

Despite having no output schema, the description explains the return semantics ('retrieve a value' or 'list all saved keys'), covers scoping, and references sibling tools. Combined with annotations, it is fully adequate for this simple one-parameter 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 schema documents the 'key' parameter with 100% coverage, but the description enriches it with real-world examples (ticker, address, research notes) and explains the key's namespace through the scoping statement, adding meaning 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 a specific action ('Retrieve a value previously saved via remember') and lists the secondary mode ('list all saved keys'). It names the resource (memory stored by remember) and distinguishes from sibling tools by describing the save/retrieve/delete lifecycle.

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 'Use to look up context the agent stored earlier' and gives concrete examples (ticker, address, research notes). It also states pairings 'Pair with remember to save, forget to delete,' making the alternative tools clear.

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