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

Annotations already declare idempotentHint=true and destructiveHint=false, and the description reinforces this ('sending the same verdict twice is harmless', 'rather than changing anything now'). It adds genuinely new context: an API key is required and the call costs no credits, which annotations do not convey.

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 tight sentences with the purpose front-loaded, followed by usage boundaries and behavioral facts. Slight redundancy between 'improves later output rather than changing anything now' and the later side-effect sentence, but nothing is wasted.

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?

With no output schema and a full-coverage input schema, the description covers the remaining gaps an agent needs — auth requirement, cost, idempotency, and explicit non-mutation of the message and lead.

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 three parameters are fully documented in the schema itself. The description adds no syntax or format detail beyond the notion of a verdict, so the baseline of 3 applies.

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?

Names a specific verb and resource ('Record ... feedback ... as training signal') and scopes it to an AI-generated outreach message for a lead. An agent can separate this from siblings like preview_message or send_to_campaign without opening the schema.

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?

States explicitly when to use it ('when the user judges a drafted message') and what it is not for ('does not edit, resend, or delete the message, and it sends nothing to the lead'). The negative boundaries are exactly the ones an agent would otherwise guess wrong about.

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