delegate

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

It discloses a non-obvious behavioral quirk: 'a run that spawns then fails returns normally.' This adds valuable operational context beyond the annotations, which only flag destructiveHint and openWorldHint. It does not contradict any annotation.

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?

Four concise sentences, each earning its place: purpose, shell prohibition, failure-mode warning, default guidance, and pointer to the skill. No redundant or filler wording.

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 10-parameter mutation tool with no output schema, the description includes the most critical operational warning and points to the delegate skill for further detail. It does not explain status-check mechanics, but the schema and skill reference compensate reasonably.

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 schema already documents all parameters well. The description adds default-keeping guidance for model, reasoningEffort, and fast, but does not deeply expand on parameter semantics. Baseline 3 is appropriate.

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 OpenAI Codex.' This clearly identifies what the tool does. It does not explicitly name the sibling tools (cancel, doctor), but the verb+resource combination is distinct enough that an agent can tell it apart.

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 explicitly instructs agents to use this tool instead of running codex from the shell, provides a clear verification step ('Check status before trusting result'), and advises keeping model, reasoningEffort, and fast at defaults unless the user asks. This is strong, actionable guidance.

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