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

Given that annotations already declare readOnly, idempotent, and non-destructive behavior, the description adds valuable context: the tool is scoped to an identifier (anonymous IP, BYO key hash, or account ID), and it can operate in two distinct modes (retrieve by key or list all keys). 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 concise and front-loaded: the first sentence gives the core action and the mode-switch behavior. The second and third sentences add use cases, scoping, and sibling relationships without any redundant 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?

For a simple one-parameter memory-retrieval tool with no output schema, the description covers the main behavior, the listing variant, the storage context, and privacy scoping. It provides enough for an agent to select and invoke the tool correctly without needing further information.

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 already describes the single 'key' parameter with 100% coverage, including the omit-to-list behavior. The description reinforces this but does not add significant new parameter-level meaning beyond what the schema provides.

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 verb ('Retrieve') and resource ('a value previously saved via remember'), and immediately contrasts this with the list-all-keys mode. It also distinguishes itself from sibling tools by naming remember and forget as the complementary save/delete counterparts.

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 the tool: 'look up context the agent stored earlier' and 'without re-deriving it from scratch.' It also provides alternative tools ('Pair with remember to save, forget to delete') and clarifies the trigger for list mode ('omit the key argument').

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