start_autopilot

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

The description discloses two important behavioral traits: it is fire-and-forget (async, non-blocking) and it 'Consumes autopilot credits.' This adds real value beyond what's in the schema. However, with no annotations provided, the description carries the full burden — it doesn't disclose cost expectations, duration bounds, cancellation ability, or failure/error behaviors. It covers the async nature and cost but is incomplete on other behavioral dimensions.

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?

Four sentences, all purposeful. The description front-loads the main purpose, then covers execution model, return value, polling mechanism, and cost in minimal words. Zero waste, no redundancy with schema field text.

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 mutating (fire-and-forget) tool with no annotations and no output schema, the description covers the essential flow: goal → run → poll status → consumes credits. It explains the return value (runId). However, it lacks details like validation feedback for bad goals, cost limits, or concurrency constraints. Given this is a side-effecting operation that consumes credits, slightly more disclosure would be warranted. Adequate but with gaps.

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 already documents both parameters (goal with example, workspace_id as optional association UUID). The description adds the fire-and-forget semantic tied to the goal and mentions returns runId, which connects the goal parameter to the workflow. It doesn't add syntax or formatting beyond the schema, so baseline 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: 'Start an AI autopilot run for outreach automation.' It clearly names the action (start), the resource (autopilot run), and the domain (outreach automation). It also describes the execution model (fire-and-forget) and how to check progress (get_autopilot_status), which distinguishes it from sibling tools like get_autopilot_status and list_autopilot_runs.

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 explains the execution flow — provide a goal, agent runs fire-and-forget, poll with get_autopilot_status — which gives clear usage context. However, it does not explicitly state when this tool should be preferred over alternatives or exclude edge cases (e.g., prerequisites like being logged in, or whether workspace_id is needed). The implied flow is helpful but lacks explicit when/when-not guidance.

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