codex

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

Annotations already flag destructive and open-world, and the description adds real value beyond them: it discloses inherited Codex login/model, incremental progress on long tasks, and — most importantly — that a failed or cancelled run may still have mutated files. What is missing is any sense of return payload beyond threadId or of concurrency/rate behavior.

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?

Five short sentences with the identity, the return value, and the two most consequential settings front-loaded. Every clause carries actionable information; the retry warning is correctly placed last as a caveat.

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?

Covers the essentials for a 10-parameter, mutation-capable, no-output-schema tool: what it returns, what it authenticates as, and what safety posture to pick. The nested config object with eight undocumented sub-fields is the one area neither the description nor schema explains.

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 the baseline is 3; the description pushes higher by adding selection guidance for sandbox (workspace-write for edits) and cwd (the project directory). It adds nothing for add_dirs, timeout_seconds, images, or reasoning_effort, which the schema already documents.

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?

States a specific verb and resource ("Run a task in a new Codex conversation") and immediately names the handoff sibling by declaring it returns threadId for codex-reply. An agent can distinguish this from codex-reply and codex-sessions without opening either schema.

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?

Gives concrete operational guidance: set cwd to the project, use sandbox=workspace-write for edits, and inspect before retrying after a failure. The threadId mention implies the follow-up path through codex-reply, though it never states explicitly when to prefer codex-reply over starting a new conversation.

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