Delegate task to Perch AI

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

With annotations already declaring destructive/openWorld/non-idempotent, the description still adds substantial context: the worker has its own bash and file read/write tools, runs against the signed-in Perch plan, and permission=take_the_wheel means it never asks before writes or commands. It also discloses the return shape and the job_id escape hatch, which is exactly the kind of behavioral detail annotations cannot carry.

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-loaded with the action and the execution model, then the guidelines flag, then the long-running flow — a sensible order with little filler. Minor redundancy: the guideline contents are listed in both the description and the guidelines parameter's schema 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 an 11-parameter open-world delegating tool with no output schema, the description covers the execution model, permission implications, billing surface, return values, and the async continuation path. Nothing an agent needs in order to call it correctly is missing, and secondary params (model, effort, persona) are fully documented in the schema.

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%, so the baseline is 3, but the description earns above that by tying two parameters to an workflow: guidelines toggles the prepended guideline block and wait_seconds bounds blocking before a job_id is returned. That causal link is not spelled out in the schema itself.

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 and resource ("Delegate a task to Perch AI (worker agent) via the official perch CLI") and immediately characterizes the resource: it runs autonomously in a working directory with its own tools. That framing distinguishes it from the sibling polling/status tools, which the description also names.

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?

Gives concrete operational guidance: use wait_seconds to bound blocking on long tasks, and poll perch_job_status when a job_id comes back; also explains that guidelines:false disables the prepended guidelines. It stops short of saying when not to delegate (e.g., trivial work better handled inline) or when perch_status beats this tool.

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