delegate

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

Annotations already flag destructive=true and openWorld=true, and the description adds useful nuance: 'agent edits,' 'ask is read-only,' and 'review runs Codex's native review.' It also sets the guardrail that model/reasoningEffort/fast should only change on user request. This enriches behavioral understanding beyond the annotations.

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?

Three sentences deliver high-value guidance with no filler. It is front-loaded with the core purpose and immediately follows with the most important rule (don't shell out), then packs mode semantics and a settings guardrail into a dense but readable structure.

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 tool's complexity (10 params, multiple modes), the description covers key operational context: mode behavior, when to use, and guardrails. It delegates deeper orchestration details to the delegate skill, which is acceptable, and the schema plus output schema fill remaining gaps. Could mention destructive consequences more directly, but annotations already flag this.

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 90%, so parameters are already well documented. The description adds valuable semantics by explaining what each mode means ('agent edits', 'plan returns a structured plan', 'ask is read-only', 'review runs Codex's native review') and reinforces that model/reasoningEffort/fast are sensitive settings.

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 the tool's function: 'Delegate a coding task to the OpenAI Codex CLI.' It differentiates from shelling out with 'Never shell out to codex — use this tool,' and enumerates mode-specific behaviors, making the purpose unmistakable.

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?

Provides strong usage guidance: tells agents to prefer this tool over shelling out, explains what each mode does, and warns against changing model/reasoningEffort/fast unless the user asks. It could more explicitly contrast with sibling tools like doctor/cancel, but the guidance is clear and actionable.

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