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

Beyond annotations (readOnly=false, idempotent=true, destructive=false), the description adds key behavioral context: memory is scoped by the agent identifier, persistent for authenticated users, and retained 24 hours for anonymous sessions. This clarifies lifespan and scoping without contradicting the annotations. No mention of overwrite behavior, but idempotent hint covers this adequately.

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 with no wasted words. It front-loads the purpose, then adds usage guidance, persistence details, and sibling relationships. Every sentence earns its place and the structure is logical.

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 2-parameter tool with no output schema, the description covers purpose, usage triggers, persistence semantics, and complementary tools. It explains enough for the agent to invoke correctly without needing to understand return values. The annotations and schema fill in the remaining safety and parameter details, making the description complete in context.

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 coverage is 100% as both parameters have descriptions. The tool description reinforces the 'key-value pair' concept and gives examples, but these examples are already present in the schema descriptions (e.g., 'findings, addresses, preferences, notes'). Thus the description adds minimal new semantic meaning beyond the schema, aligning with the baseline of 3.

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 clear verb+resource: 'Save data the agent will need to reuse later' and specifies it works across conversations/sessions. It distinguishes from siblings by explicitly naming recall and forget as complements, making the tool's role in the memory trio unambiguous.

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?

Provides explicit usage guidance: 'Use when you discover something worth carrying forward' with concrete examples like ticker, address, preference, research subject. It also tells the agent to pair with recall for retrieval and forget for deletion, effectively outlining when to use this tool versus its siblings.

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