delegate

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

With no annotations, the description carries full burden. It discloses behavioral traits: asynchronous behavior (mode), safety modes (read_only/propose/write/yolo) with trust requirements, session resumption, and return of job ids. Minor gaps include error handling and CLI availability.

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 concise, front-loaded with purpose, and each sentence adds value. Structured with bullet-like clarity, no redundancy.

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?

Given the complexity (12 parameters, async modes) and presence of an output schema, the description covers essential behavioral context. Missing parameter explanations for half the parameters, but the tool remains usable for an AI agent.

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 0%, so the description must compensate. It explains key parameters (cli, model, safety_mode, mode, session_id, trust_workspace) but omits prompt, working_dir, files, role, timeout_s, include_raw. The explained parameters add significant value beyond 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?

The description clearly states 'Delegate a task to one CLI and return its normalized result', providing a specific verb and resource. It distinguishes from siblings by mentioning adapter ids (see capabilities) and async mode, though not explicitly compared.

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 usage contexts like safety modes and async mode but lacks explicit guidance on when to use this tool versus its siblings (capabilities, consensus, etc.). It provides parameter-level guidance but not tool selection advice.

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