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

Annotations already declare read-only, idempotent, and non-destructive, so the bar is lower. The description adds valuable context about scoping to the agent's identifier (anonymous IP, BYO key hash, or account ID) and the list-all behavior when key is omitted. It does not cover return format or error cases, but for a simple retrieval tool this is adequate.

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 three sentences with no fluff. It front-loads the core behavior, then provides usage examples, scoping details, and sibling relationships. Every sentence earns its place.

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?

With only one optional parameter, no output schema, and good annotations, the description is complete. It covers purpose, usage context, scoping, and relationships to remember/forget. No significant gaps.

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?

Schema description coverage is 100%, so the baseline is 3. The description adds meaning by specifying the key must have been 'previously saved via remember' and clarifies the omission behavior, which complements the schema's own 'omit to list all keys'.

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 retrieves a previously saved value or lists all saved keys, with a specific verb ('retrieve') and resource ('value'/'keys'). It distinguishes itself from siblings by naming 'remember' and 'forget' and clarifying its complementary role.

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 when to use it ('Use to look up context the agent stored earlier') and provides a clear alternative/exclusion by pairing with 'remember' to save and 'forget' to delete. It also implies not to use it for new information by saying 'without re-deriving it from scratch'.

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