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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the tool is clearly read-only and safe. The description adds useful behavioral context beyond annotations: the ability to both retrieve a specific value and list all keys, and that the scope is tied to the caller's identifier. No contradictions with annotations. It does not detail rate limits or error handling, but the annotations cover the safety profile.

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 long, front-loaded with the core purpose. Each sentence adds value: the first defines the action, the second gives examples and motivation, the third adds scoping and pairing. There is no redundant or extraneous information. Could be slightly more concise by combining scoping with the first sentence, but overall efficient and well-structured.

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, annotations present), the description covers the essential aspects: what it does, how to use it (with and without key), the scope, and its relationship to remember and forget. It does not explain return values or error handling, but that is acceptable for a straightforward retrieval tool. The descriptions of sibling tools (remember, forget) provide complementary context. Overall complete enough for an agent to use correctly.

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% — the single optional parameter 'key' has a clear description: 'Memory key to retrieve (omit to list all keys).' The description reinforces this by stating 'list all saved keys (omit the key argument)', but adds no new details about the parameter's format or constraints beyond what the schema provides. Baseline is 3 due to high coverage, and the description adequately complements the schema without adding significant new info.

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' or 'list') and the resource (memory values saved via remember). It specifies two modes: retrieving a value by key, or listing all keys by omitting the argument. It also gives concrete examples of what the stored context might be, such as 'user's target ticker, an address, prior research notes', distinguishing it from sibling tools like remember and forget.

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 explicit when-to-use guidance: 'Use to look up context the agent stored earlier ... without re-deriving it from scratch.' It implicitly tells when not to use (for saving or deleting) by pairing with remember and forget. It also explains scoping: 'Scoped to your identifier (anonymous IP, BYO key hash, or account ID).' However, it does not explicitly mention alternative tools or situations where a different retrieval method might be preferable, but overall it's clear for a simple memory tool.

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