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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds the key behavioral trait that the memory is 'Scoped to your identifier (anonymous IP, BYO key hash, or account ID),' which is crucial for agents to understand visibility. It also clarifies the list-all behavior when the key is omitted. No contradictions with annotations; the description supplements them well.

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 consists of three concise sentences: the first defines the core functionality, the second explains when to use it with examples, and the third covers scoping and complementary tools. Every sentence adds value without redundancy.

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 tool with one optional parameter, no output schema, and robust annotations, the description covers what the tool does, when to use it, how the key parameter behaves, and the scope of memory. It could mention behavior for a missing key, but given the simplicity and natural semantics of retrieval, the description is sufficiently complete.

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's 100% coverage of the single 'key' parameter already documents its semantics. The description enriches this by providing concrete examples of key contents (user's target ticker, address, prior research notes) and restating the omit-to-list behavior, giving agents a better sense of what keys are appropriate. This goes beyond mechanical schema details.

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 explicitly states the action ('Retrieve a value previously saved via remember, or list all saved keys') and differentiates from sibling tools by naming 'remember' and 'forget' as companions. It provides concrete examples of use cases (target ticker, address, research notes), making the purpose unmistakable.

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 gives clear guidance: 'Use to look up context the agent stored earlier... without re-deriving it from scratch.' It also explicitly mentions pairing with 'remember' to save and 'forget' to delete, establishing when to use this tool versus alternatives.

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