delegate

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

The description discloses critical behavioral traits beyond the annotations, notably 'Auto-approves every permission the agent requests, in any mode and anywhere on disk,' which deepens the destructiveHint=true annotation. It also warns that plan/ask modes are 'not enforced by the bridge' and advises reviewing the git diff after every run, adding transparency about the tool's actual safety guarantees.

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 dense but every sentence adds value—purpose, usage rule, defaults, plan workflow, auto-approval warning, response summary, and pointer to the skill. It is front-loaded with the core purpose and remains structured without 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?

For a complex, high-risk tool, the description fully covers usage, defaults, behavioral warnings, workflow steps, and return contents even without an output schema. It explicitly notes the auto-approval behavior, plan/ask limitations, and what results are returned, giving an agent enough to invoke it safely.

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?

While the schema already covers 89% of parameter meaning, the description enriches usage semantics for key parameters: spec ('inline vs file path'), default mode/model, and resumeSessionId for answering clarifying questions. Since schema coverage is high, the value is additive rather than exhaustive; it doesn't detail less-common params like context and reasoning, but the schema itself describes them thoroughly.

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 a specific verb and resource: 'Delegate a coding task to cursor-agent over ACP.' It further distinguishes the tool from the alternative of shelling out to cursor-agent ('Never shell out to cursor-agent — use this tool only'), making the purpose unmistakable. The sibling tools cancel and doctor are clearly different in scope.

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?

It explicitly instructs when to use this tool versus the alternative: 'Never shell out to cursor-agent — use this tool only.' It also provides clear operational guidance for plan mode and resuming sessions ('Plan workflow: mode=plan, then resume with mode=agent and resumeSessionId') and explains how to answer clarifying questions by resuming.

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