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

Beyond the annotations (readOnly, idempotent, destructive=false), the description adds critical behavioral details: the 'omit key' listing behavior and the scoping to an identifier (anonymous IP, BYO key hash, or account ID). This explains privacy and namespacing, 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?

The description is three sentences, each with a distinct purpose: function, use case, and scoping/companion tools. It is front-loaded with the primary action and free of filler or repetition.

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 retrieval tool with one optional parameter and strong annotations, the description covers the essential behaviors (retrieve, list, scope, pairing). It lacks explicit error/return value details, but the absence of an output schema and the tool's simplicity make the description adequate.

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 fully describes the 'key' parameter (including 'omit to list all keys'), so the description doesn't add new parameter semantics. The examples of key contents are helpful but redundant to the schema's coverage.

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 with specific verbs: 'Retrieve a value previously saved via remember' and 'list all saved keys'. It distinguishes itself from sibling tools by explicitly naming remember (save) and forget (delete), making the tool's niche unambiguous.

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: 'Use to look up context the agent stored earlier' with concrete examples (target ticker, address, research notes) and contrasts with re-deriving data. It implies the when-not-to-use by mentioning the companion tools (remember/forget), though it doesn't explicitly list exclusion scenarios.

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