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

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds meaningful behavioral context: it uses REAL Customer Evidence first when available, then falls back to a labeled simulated ICP, and it returns honest engagement-oriented feedback.

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?

Three focused sentences cover what the tool does, what it returns, and when to use it. The phrasing is slightly metaphorical ('customer truth'), but the added explanation keeps it efficient and readable.

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 read-only evaluation tool with complete parameter schema and clear annotations, the description is largely sufficient. It explains the process, output, and usage context; only a more concrete output format would make it fully complete, and there is no output schema to supply that.

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%, so the schema already documents all parameters. The description does not add further meaning about parameters like target_icp or deliverable_type, so it neither helps nor hurts beyond the baseline.

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 what the tool does: it evaluates a deliverable against customer evidence and simulated ICPs, then returns feedback. It is distinct in substance from generic review tools, but it does not explicitly name or contrast any sibling 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?

The description gives explicit guidance: 'Use on customer-impact deliverables before sending.' It establishes a clear context and timing for use, though it does not provide when-not-to-use guidance or name alternatives.

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