fleet_run

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

With no annotations, the description carries the full burden. It discloses that the tool returns the agent's response, mentions headless execution, and warns that codex/agy can edit files and run commands. It does not cover error/timeout behavior, but the key safety and output traits are addressed.

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 compact, front-loaded with the main purpose, and each sentence earns its place. It avoids redundancy while packing essential details into four short sentences.

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?

The description is complete for a tool of this complexity, covering purpose, use cases, machine mapping, agent capabilities, and output. It could mention timeout/default behavior or return format specifics, but these are partially covered by the schema and not critical for invocation.

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%, yet the description adds value by mapping machine enum values to human-readable meanings (wsl=local, draydev=dev VM, ec2=prod) and describing agent CLI capabilities. This goes beyond the schema's generic descriptions.

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 identifies the action ('Delegate a single prompt to another agent CLI'), the resource (claude, codex, or agy), and the environment (fleet machines). It explicitly states the return value and gives use cases, distinguishing it from sibling tools like fleet_review and fleet_status.

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 use cases: 'Use to farm a subtask to a different model, or to run work on a remote box.' It also includes a warning about codex/agy capabilities and advises scoping prompts, but it does not name alternative tools for exclusion.

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