codex_raw

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

No annotations are present, so the description must carry the full disclosure burden. It reveals only that a model-override env var still applies. It does not mention that executing arbitrary arguments may have side effects, security implications, or that the process output/error format is. This is a significant gap for an escape-hatch tool.

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?

Two sentences, with the primary purpose front-loaded and the escape-hatch positioning in the second sentence. Every word earns its place; no fluff or redundant detail.

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?

Despite the tool's raw nature, the description is incomplete for an agent that must call it safely. It does not state what the tool returns (stdout, exit code, etc.), whether it is synchronous, or warn about the risk of passing arbitrary args. Given no output schema and no annotations, more context is needed for correct invocation.

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 75% (only args lacks a description). The description adds minimal meaning beyond the schema: 'arbitrary argument array' clarifies the args type but does not explain cwd, env, or timeoutMs further. Since coverage is high and the description contributes a small extra for args, a baseline of 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?

States a clear verb-resource pair ('Run the Codex CLI') with a specific scope ('arbitrary argument array') and positions itself as an escape hatch relative to the other sibling tools. This distinguishes it from codex_run and the rest without needing to inspect schemas.

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?

Explicitly says to use it when 'options not covered by the other tools' are needed. This gives a direct condition for selection, though it does not name specific sibling tools or give excluded use cases. Still, the core guidance is unambiguous and useful.

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