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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so safety is covered. The description adds meaningful behavioral context beyond that: the tool is scoped to an identifier ('anonymous IP, BYO key hash, or account ID'), and the ability to list all keys by omitting the argument is described. It does not detail return formats or error behavior, but the added scoping info is valuable.

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 earning its place: the first states the action and modes, the second provides usage context with examples, and the third covers scoping and companion tools. It is front-loaded with the core function and contains no filler or 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?

Considering the tool's simplicity (one optional parameter, no output schema), the description covers both invocation modes, scoping, and usage intent. However, it does not describe the return value format or behavior when a key is not found, which would be useful given the absence of an output schema. Overall, it is nearly complete but has a small gap.

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 already provides 100% coverage for the single 'key' parameter with the description 'Memory key to retrieve (omit to list all keys)'. The tool description repeats this information ('omit the key argument') but adds no new semantic detail beyond what the schema already conveys. Thus the description does not significantly elevate understanding of the parameter.

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 opens with a specific verb and resource: 'Retrieve a value previously saved via remember, or list all saved keys (omit the key argument).' It clearly distinguishes this tool from siblings by directly naming remember (save) and forget (delete), and explains the dual modes of operation. This is unambiguous and fully differentiates the tool.

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?

It provides clear context for when to use the tool: 'Use to look up context the agent stored earlier' with concrete examples (target ticker, address, research notes). It also names companion tools for alternatives (remember to save, forget to delete). However, it does not explicitly state when NOT to use it (e.g., when to prefer search), though this is implied by the focus on previously stored memory.

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