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

Annotations already convey read-only and non-destructive behavior. The description adds valuable behavioral context beyond annotations by explaining the scoping mechanism (anonymous IP, BYO key hash, account ID) and the dual-mode behavior (retrieve vs. list). This is useful for an agent to understand the tool's operational boundary, though it could go further with details about missing-key behavior.

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 sentences long, front-loaded with the primary action, and includes concrete examples and necessary caveats (scoping). It avoids redundancy with the schema and annotations, earning its length. No filler or unnecessary detail.

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?

Given the tool's simplicity (one optional parameter, no output schema), the description fully covers the functionality: both retrieval and listing modes, the source of saved values (via remember), and scoping context. It is complete enough for an agent to use the tool correctly without additional 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 provides 100% coverage of the single optional parameter 'key' with a clear description ('omit to list all keys'). The tool description repeats this behavior but does not add significant new meaning beyond the schema. Thus the baseline of 3 applies, as the description doesn't compensate further.

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 saved via remember, or list all saved keys when key is omitted. It distinguishes itself from sibling tools (remember and forget) by explicitly positioning itself as the retrieval counterpart, and the verb 'retrieve' is specific and action-oriented.

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 provides clear usage context, such as 'look up context the agent stored earlier' and concrete examples (ticker, address, research notes). It also gives indirect guidance about when to use it versus alternatives by mentioning 'pair with remember to save, forget to delete,' though it doesn't explicitly state exclusions or when not to use it.

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