codex-reply

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It mentions the deprecated alias and timeout parameter, but does not specify side effects, error behavior when the thread does not exist, whether results are streamed or returned in full, or any authentication/permission requirements. This is a minimal disclosure for a tool that sends prompts and likely mutates session state.

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 two sentences with no redundant text. The primary purpose is stated first, followed by useful context about the tool's provenance and deprecated alias. Every phrase carries meaning, making it efficiently scannable for an agent.

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?

Given the lack of annotations, output schema, and 0% schema coverage, the description is incomplete. An agent would not know what constitutes a valid `threadId` format, how `timeout-seconds` behaves, what errors may occur, or what the response format looks like. This is a significant gap for a tool that requires a user-provided identifier and prompt.

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 0%, so the description must add meaning to parameters. It clarifies that `conversationId` is a deprecated alias for `threadId`, which is helpful. However, it does not explain the `prompt` parameter beyond being a follow-up prompt, nor does it describe `timeout-seconds` semantics (e.g., what happens on timeout). It partially compensates for the missing schema descriptions but leaves key parameters under-explained.

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 a specific purpose: continuing an existing Codex thread with a follow-up prompt. It identifies the resource (existing thread) and distinguishes itself from the sibling `codex` tool by noting the thread is started by `codex`, making the differentiation explicit.

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 conveys when to use this tool (when continuing an existing thread, including a previous session) and implies that `codex` is for starting threads. However, it does not explicitly state 'use this instead of `codex` when a thread already exists,' but the context is strong enough. It also clarifies the deprecated `conversationId` alias, which guides parameter selection.

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