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

The description goes well beyond the annotations by disclosing the hourly proposal loop, emphasizing that nothing sends without approval, and explaining the approval_token round-trip behavior. It also clarifies that dashboard guardrails apply, giving the agent a clear safety model.

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?

Every sentence earns its place: the first states the primary action, the second discloses the side effect and approval guarantee, and the third explains the guarded two-step protocol. It is front-loaded and compact despite covering complex behavior.

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 tool with no output schema, the description covers the essential invocation flow, error shape, approval mechanism, and safety equivalence to dashboard actions. An agent has enough information to call it correctly and to know what to expect when confirmation is required.

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 documents all three parameters with 100% coverage, so a baseline of 3 is appropriate. The description adds cross-parameter meaning by explaining how approval_token interacts with the rest of the call and when it is required, which goes beyond individual schema descriptions.

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 concrete verb and resource pair: 'Turn the Discovery Autopilot on or off, and/or set the commission offer.' This clearly states the action and scope, and it is distinguishable from sibling tools like get_autopilot or approve_autopilot_action.

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 guarded-flow instructions are explicit: call without approval_token to get an approval_required response, then call again with the token. This gives clear procedural context, though it does not explicitly contrast the tool with siblings such as approve_autopilot_action or state when not to use it.

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