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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description adds value by revealing scoping per identifier (anonymous IP, BYO key hash, account ID) and the lifecycle with remember/forget. This goes beyond the annotations without contradicting them.

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 concise at about 70 words, front-loading the core action and then providing usage context, scope, and paired tools. There is minor redundancy ('previously saved via remember' and 'stored earlier'), but overall every sentence contributes meaning.

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 read-only tool with one optional parameter and no output schema, the description adequately covers purpose, usage scenario, scoping, and workflow. It omits only minor details like behavior when a key is not found, which are not critical for operation.

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 documents the 'key' parameter with 100% coverage, so the baseline is 3. The description adds real-world examples of key types (ticker, address, notes) and clarifies the omit-key behavior, providing extra semantic context that helps an agent understand how to invoke the tool.

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 previously saved values or lists all saved keys, using specific verbs and resource nouns. It distinguishes itself from sibling tools by explicitly pairing with remember and forget, and by describing the unique 'list all keys' behavior.

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 context for when to use the tool ('to look up context the agent stored earlier... without re-deriving it from scratch'). It also mentions pairing with remember and forget, but does not explicitly exclude alternative tools like search_within. This is clear but lacks direct '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.