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

Annotations are minimal (openWorldHint, destructiveHint) and do not mention the real-money impact. The description fully compensates by detailing financial implications: 'CAN SPEND REAL MONEY,' cost per credit, order placement conditions, and limits on domains/mailboxes. It also specifies that nothing happens before the call and that sending starts after. This is exemplary transparency beyond annotations.

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 lengthy but every sentence carries critical information: purpose, financial risk, conditions, and prerequisites. It front-loads the core purpose and then layers constraints. While not terse, the density is justified given the high-stakes nature of the operation.

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 complexity (monetary transactions, conditional behavior, caps), the description covers all necessary details: what happens, what fails, the need to show the plan first, and the irreversible nature after the call. There is no output schema, but the description does not need to explain return values for a confirmation action. It is complete for correct invocation.

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 single parameter 'id' is fully documented in the schema with description and constraints. The tool description does not add new semantics about the parameter, but the schema covers it 100%. Since the schema does the heavy lifting, the baseline of 3 is appropriate.

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 states a specific verb, resource, and context: 'approves an autopilot run that is awaiting approval — the one human gate in the flow.' It clearly distinguishes this from siblings like start, pause, resume, and kill by focusing on the approval action. The purpose is immediately clear without confusion.

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 clear usage context: it is the human-gate step, and it instructs to 'Show the user the plan from the start_autopilot_run response before calling this.' It also clarifies the consequences (sending starts without further confirmation). It does not explicitly name alternatives but implies its unique role in the flow, making it distinguishable from related tools like kill_autopilot_run.

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