codex_prepare_agent_control

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

The description adds meaningful behavioral context beyond the annotations: it discloses the fail-closed behavior and explicitly states that no proposal or host state is created, consistent with readOnly and idempotent hints. This goes beyond what annotations alone provide, though it does not describe potential side effects or failure modes in detail.

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 concise and front-loaded with the fail-closed condition. It contains only two sentences with no redundant phrasing. The structure is direct and avoids fluff, though the content is cryptic; still, it is appropriately sized for a tool with one parameter.

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 lacks a clear statement of the tool's primary function and does not explain the 'action' parameter's options. It also provides no information about return values or usage context. Even with annotations and an output schema, an agent would not know what this tool does or how to invoke it correctly, making the description inadequate.

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?

The single parameter 'action' has an enum of 'disable', 'enable', 'stop_active', but the description provides no explanation of these values or their semantics. With 0% schema description coverage, the description should compensate, but it does not mention the parameter at all. The agent is left to infer meaning from the enum names alone, which is insufficient.

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 does not explicitly state that the tool enables, disables, or stops active agent control. Instead, it only mentions a fail-closed precondition and a contract gap, leaving the core action implicit. The name and the 'action' parameter hint at the purpose, but the description itself is vague and does not clearly articulate what operation is being prepared.

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?

No guidance is given for when to use this tool versus any sibling tools. The only condition mentioned is 'Fail closed unless a protected Codex host broker is available,' which is a safety precondition rather than selection guidance. There is no discussion of alternatives, prerequisites, or appropriate contexts.

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