Read messages from Codex

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

Annotations already signal read-only/non-destructive behavior; the description adds non-blocking/cost characteristics, cursor-based incremental reads, and the meaning of awaiting_answer. It could go slightly deeper on message retention or consumption behavior, but the key traits are disclosed.

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 tight sentences lead with purpose and examples, then move to usage and behavioral guidance. There is no repetition of schema/annotations and no filler.

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 simple read-only tool with one optional parameter, it covers purpose, cost, non-blocking behavior, pagination, and a key return field. It does not fully describe the message envelope shape or when to use codex_job_logs instead, but the overall guidance is sufficient 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?

The schema already documents job_id with 100% coverage, so the description does not need to compensate. It adds no parameter-level detail, and the baseline of 3 applies because the schema carries the semantic load.

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 uses concrete verbs ('Collect'/'Read') and a specific resource ('messages from Codex'), with examples of content types (questions, findings, warnings). This clearly distinguishes it from log/status/reply sibling tools.

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?

It gives clear context: the tool is cheap, non-blocking, and worth calling between other tools while a run is in flight. It also provides pagination guidance via next_cursor, though it does not explicitly contrast with siblings or state when not to use it.

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