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

Annotations already indicate safe, read-only, idempotent behavior. The description adds that the tool is scoped to an identifier and that omitting the key changes behavior to listing all keys. While no contradictions exist, the description does not disclose return format, error handling (e.g., missing key), or pagination for listing, which would enhance transparency.

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?

Four sentences, front-loaded with the primary purpose and immediate usage. Every sentence adds unique value: primary action, usage context, scoping, and pairing with siblings. No wasted words.

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?

The description adequately covers retrieval and listing, but without an output schema, it should explain the return format (e.g., what the value looks like, how keys are listed) and error cases (key not found). The examples in the schema help, but the description itself is incomplete for a simple tool with no output schema.

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 has 100% coverage for a single optional string parameter. The description adds critical meaning: omitting the key lists all keys, while providing it retrieves a specific value. This goes beyond the schema's property description ('Memory key to retrieve (omit to list all keys)') by framing it in the context of the tool's dual behavior.

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 value by key or lists all keys if omitted. 'Retrieve' and 'list' are specific verbs, and the resource ('value previously saved via remember' / 'saved keys') is unambiguous. This distinguishes it from its siblings 'remember' (save) and 'forget' (delete).

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 explains when to use this tool: 'to look up context the agent stored earlier... without re-deriving it from scratch.' It provides concrete examples (target ticker, address, research notes) and mentions scoping by identifier. It explicitly pairs with 'remember' and 'forget', though it does not provide explicit 'when not to use' guidance.

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