start_autopilot

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

This description goes far beyond annotations. It discloses critical behavioral traits: it sends real messages without returning for approval, it consumes credits and requires an API key, and it runs concurrently. Annotations only indicate readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, but the description adds vital risk awareness (consequential, fire-and-forget) that the agent needs.

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 well-structured: a brief overview sentence, then a high-risk warning paragraph, and finally a note about resource consumption. Each sentence earns its place, and the most critical information (sends real messages, requires explicit user request) is front-loaded. No fluff or redundancy.

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?

Despite no output schema, the description clearly states it returns a runId and how to monitor progress. It covers prerequisites (API key), side effects (credit consumption, concurrent runs), and constraints (goal text is the brief). This is complete for a complex, high-stakes tool.

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?

Although the schema already describes both parameters (goal and workspace_id) with 100% coverage, the description adds important context: the goal text is 'the entire brief' and gives an example, implying its critical role. It doesn't explain workspace_id further, but that's fine because the schema covers it. The description reinforces the meaning of goal beyond the schema's generic example.

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 starts an autonomous outreach run, distinguishes it from sibling tools (like list_leads or get_autopilot_status), and specifies the core functionality: the agent finds, contacts, and follows up with leads. The phrase 'FIRE-AND-FORGET' and 'SENDS REAL MESSAGES TO REAL PEOPLE' makes the resource and action unambiguous.

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 guidance on when to use it (only when the user has explicitly asked for one and understands the goal) and when not to (it's consequential, not for casual experimentation). It also mentions alternatives for monitoring: 'watch progress with get_autopilot_status.' It notes that each call starts a separate run, implying warning against duplicate invocations.

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