codex_run

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

No annotations are provided, so the description bears full burden. It discloses authentication and specialization but does not describe side effects, safety profile, or behavior such as file writing. The sandbox parameter in the schema provides some context, but the description itself is insufficient.

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 three sentences, each adding distinct information: action and target, specialization, and authentication note. No wasted words; front-loaded with purpose.

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 covers basic functionality and specialization but omits return format, error behavior, or additional context. Given no output schema and moderate complexity, it is adequate but not comprehensive.

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 baseline is 3. The description adds minimal value beyond the schema; it mentions specialization (relevant to prompt) and cached auth, but does not elaborate on parameters like model or timeout beyond what schema already provides.

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 sends a task to OpenAI Codex via local CLI. It specifies specialization in coding tasks, file operations, and technical analysis, and mentions cached auth. This distinguishes it from sibling tools like claude_run and gemini_run.

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 implies use for coding tasks and technical analysis, and notes no API key required. However, it does not explicitly state when to use versus alternatives or provide exclusions. Context is present but lacks explicit guidelines.

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