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

Annotations already mark destructive/openWorld/not-idempotent, and the description adds substantial context beyond them: fire-and-forget with no approval loop, real messages sent to real people, credit consumption across multiple pools, API key requirement, and the runId return. It explains side effects the annotations only gesture at.

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?

Front-loads the consequential warnings and the fire-and-forget nature before mechanics. Every sentence carries distinct, action-relevant information (approval, credits, API key, concurrency) with no padding.

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 high-stakes no-output-schema tool, the description covers the return value (runId), the monitoring path, credit/auth prerequisites, and concurrency behavior. Nothing an agent needs to call it safely is missing.

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 coverage is 100% and the schema already documents both parameters with examples. The description adds only the framing that 'the goal text is the entire brief', which is useful but marginal against a fully documented schema.

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?

States a specific verb+resource (start an autonomous outreach run) plus scope (agent finds, contacts and follows up on its own). It is clearly distinguished from siblings like get_autopilot_status and list_autopilot_runs, which are referenced by name for monitoring.

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?

Explicitly states when to use ('only start a run when the user has explicitly asked for one') and names the alternative for tracking progress (get_autopilot_status). It also warns that each call spawns a separate concurrent run against the same goal, covering the when-not condition.

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