pilot

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

No annotations are provided, so the description must carry the transparency burden. It says 'execute it using its full toolkit' and includes examples of mutating actions (e.g., 'Send a LinkedIn connection request', 'Book a meeting', 'Pause my cold email campaign'). However, it does not explicitly disclose potential side effects, reversibility, or that actions will have real-world consequences. This is a moderate disclosure gap.

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 long but well-structured with an opening summary, a clear usage directive, and categorized bullet examples. Every section adds practical value for an agent. It is not bloated with unrelated content, and the organization makes it easy to scan.

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 complex tool with no output schema and no annotations, the description thoroughly covers use cases and scope, which is critical. However, it omits any information about return values/response format, error handling, or potential limitations. Since there is no output schema, the description should have provided some indication of what the agent can expect in response.

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 input schema describes 'message' as 'Natural language instruction' and 'thread_id' as optional context. The description adds substantial value by providing a large set of concrete example instructions across domains, enriching the semantics of the message parameter beyond the schema. It does not discuss thread_id, but the coverage is already high and the examples more than compensate.

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 'The OutreachPilot AI engine. Send any natural language instruction and Pilot will execute it using its full toolkit.' This clearly states a specific verb (execute), resource (full toolkit), and differentiates from simple CRUD siblings by stating 'beyond simple CRUD.'

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 explicitly says 'Use this for complex or multi-step tasks that go beyond simple CRUD.' This provides clear guidance on when to use the tool versus the specific sibling CRUD tools. The extensive categorized examples further illustrate the appropriate contexts without ever being vague.

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