Background Computer Use

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

The description adds significant behavioral context beyond annotations: it details that safe mode is list-only, full permissions never bypass first-party controls, and calls consume separate Codex usage. Annotations mark destructiveHint=true and readOnlyHint=false, which the description reinforces with specifics.

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 a single paragraph that efficiently conveys key behavior, mode implications, and constraints. It could be structured more clearly but is not overly verbose.

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 purpose, mode selection, safety guarantees, and resource consumption. With no output schema, it does not describe return values, but the tool's complexity is well-addressed given the annotations and schema.

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% with all parameters described. The description adds value by explaining the mode enum semantics (safe vs full permissions) and how parameters like cleanup relate to overall process.

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 uses the official Codex Computer Use broker for native macOS apps, with specific modes (list, inspect, act, dictionary_lookup). It distinguishes from the sibling status tool by focusing on execution of computer use actions.

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 explains when to use safe mode (list-only) vs full permissions (inspect/act/dictionary_lookup) and mentions separate Codex usage. However, it does not explicitly exclude use cases that the sibling status tool would handle.

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