Send Codex a message

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

Annotations already carry destructive and non-read-only hints. The description adds useful behavioral detail: delivery happens at next tool turn (non-interrupting) and omitting job_id broadcasts to all runs. This exceeds annotation baseline.

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, front-loaded with purpose, no filler. Every phrase contributes useful information.

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?

For a two-parameter tool with no output schema, the description covers the message content, targeting, and delivery timing. It is complete enough for correct invocation, though it does not address edge cases like missing runs.

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 covers 100% of parameters. The description adds semantic nuance by explaining that omitting job_id reaches all runs and is intended for stop, which goes beyond the schema's phrasing.

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 action (send a message to a running Codex agent) and enumerates use cases (correction, direction change, stop). It distinguishes itself from siblings by emphasizing unsolicited messages and delivery timing, so an agent can separate it from codex_reply or codex_job_cancel.

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 scenarios (correction, direction change, stop) and parameter guidance (omit job_id to reach every run, especially for stop). It does not explicitly name alternative tools, but the context is clear enough for selection.

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