submit_lead_feedback

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds value by explaining the idempotent behavior ('sending the same verdict twice is harmless') which aligns with and explains the annotation. It also discloses requirements (API key) and cost (no credits) beyond annotations. However, it doesn't detail what happens to the feedback record or any state changes, so a 4 is appropriate.

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 and structured with a clear opening sentence about purpose, followed by usage guidance, and then behavioral details. Every sentence carries weight, and it is front-loaded with the primary action. No filler or redundant information.

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?

Given the tool's complexity (simple write operation with three params), the schema fully describes parameters, and annotations cover safety and idempotency, the description provides sufficient context: purpose, when to use, what it doesn't do, and side effects. No output schema needed, and the description explains the long-term effect ('improves later output'), which is valuable. Complete for an agent to decide and invoke correctly.

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 fully documents all three parameters (jobId, leadEmail, feedback). The description doesn't add much beyond the schema; it mentions 'feedback' as a verdict but doesn't elaborate on how jobId or leadEmail are used. Baseline 3 is correct when schema fully covers parameters.

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's purpose: recording feedback on AI-generated outreach messages as training signal. The verb 'Record' with the resource 'lead feedback' is specific, and it distinguishes itself from sibling tools like 'preview_message' and 'send_to_campaign' by clarifying it does not edit, resend, or delete the message.

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 explicit usage guidance: 'Use it when the user judges a drafted message — it improves later output rather than changing anything now.' It also clarifies what it does not do (edit, resend, delete, send to lead), which helps differentiate from similar messaging tools. This exceeds a 4 by providing both positive and negative conditions for use.

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