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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that the prompt is passed verbatim, that results include file paths and inline previews with downscaling for oversized files, that generation often exceeds wait_sec returning a status and job_id, and how to retrieve results. It also discloses defaults and quality trade-offs. This is exceptionally transparent for a tool with zero annotation support.

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 five sentences, each earning its place: the core action, the pass-through behavior, the return format, the default quality guidance, and the asynchronous fallback. It front-loads the primary purpose and packs essential behavioral details without redundancy or fluff.

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 tool with 8 parameters, 100% schema coverage, and no output schema, the description covers everything an agent needs: the synchronous/asynchronous split, how to handle long runs, the default quality and size, and the inline display behavior. Sibling tools are correctly referenced for follow-up, and the description is self-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?

Schema coverage is 100%, so a baseline of 3 applies. The description adds value by explaining the practical impact of quality (draft vs. final), the wait_sec/job_id behavior, and the inline preview downscaling. It doesn't rehash schema definitions but provides usage-level meaning for key parameters, exceeding the baseline.

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 opens with a specific verb and resource: 'Generate images with the local Codex CLI.' It clearly differentiates from siblings (codex_job_result, codex_read_artifact, codex_run) by focusing on image generation, while the others handle results, artifacts, and generic execution. The scope is unambiguous and an agent can immediately tell this tool's purpose.

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 provides clear operational context: it explains the default draft behavior, quality guidance for final assets, and explicitly tells the agent to call codex_job_result when a job_id is returned. However, it does not explicitly state when to avoid this tool or when to prefer a sibling (e.g., 'use codex_run for non-image tasks'), though the name and content make that implicit. This is a minor gap, so not a perfect 5.

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

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

With no annotations, the description carries the behavioral burden and does well: it discloses that the tool waits up to wait_sec, that polling may need to be repeated, and that results persist for 60 minutes. It does not describe response statuses in detail, but the core polling behavior is transparent.

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?

Three sentences convey purpose, usage condition, polling behavior, and retention in a compact, front-loaded structure. There is no filler or redundancy.

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 is sufficiently complete for a simple polling tool with two well-documented parameters. However, there is no output schema, so the description could have been more explicit about the response shape or status values returned after waiting. Still, the essential invocation workflow is clear.

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 input schema already describes both parameters fully, including that job_id comes from codex_run or codex_generate_image and that wait_sec defaults to 45 with a maximum of 50. The description reinforces these facts but adds little semantic value beyond them, so baseline 3 is appropriate.

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 specifies a distinct action: retrieving the result of a codex_run or codex_generate_image call that previously returned status: running. It names the exact operation, resource type, and state condition, making it unmistakable from siblings that start jobs or read artifacts.

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 gives strong usage context: it is meant for jobs that returned status: running, and it instructs the agent to call again if the job is still running. It does not explicitly contrast with codex_read_artifact or list when not to use this tool, but the operational guidance is clear.

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

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

No annotations are provided, so the description carries the full burden. It adds useful behavior beyond the schema by stating that images are returned as image content and everything else as text. However, it does not disclose error handling, permission requirements, or what happens with nonexistent files—gaps that would matter for a read tool.

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 short sentences with no filler. The purpose is front-loaded, and the output-type behavior is stated succinctly. Every sentence earns its place.

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 tool with two parameters and full schema documentation, the description covers the key context: what file to read and how the content will be returned. It lacks explicit error handling and edge-case details, but does not need to explain return values since there is no output schema and the description handles output type.

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 description coverage is 100%, so both parameters are already documented. The description adds no parameter-specific guidance, but it does not need to because the schema fully covers path and max_bytes semantics. This matches the baseline for full schema coverage.

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 states a specific verb ('Read'), a resource ('one file from a Codex workspace'), and the purpose ('artifacts that were too large to inline'). It also differentiates from siblings by clarifying that it reads files, while codex_generate_image generates images and codex_run likely executes tasks.

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 gives the clear context 'for artifacts that were too large to inline,' which tells an agent when to reach for this tool. It does not explicitly name alternative tools or state exclusions, but the use case is specific enough to strongly infer when it applies.

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

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

With no annotations, the description carries full behavioral disclosure. It reveals side effects (writing/running code, installing packages), isolation ('inside an isolated workspace folder'), and async behavior with wait_sec and job_id. It does not mention error conditions or persistence of created files beyond the return statement, but covers the main behavioral risks and control flow.

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?

Three sentences with no filler. The main action, behavioral scope, and async fallback are all front-loaded and each sentence contributes distinct information needed to select and invoke the tool correctly.

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 five-parameter, async, no-output-schema tool, the description covers purpose, side effects, async behavior, and continuation semantics. It doesn't specify what the final result payload looks like or how timeout_sec interacts with wait_sec, but what an agent needs to make a correct call and collect results is present.

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%, so the baseline is 3, but the description adds meaningful semantics: it explains that wait_sec controls the sync/async split, that a job_id should be passed to codex_job_result, and that reusing workspace continues work on the same files. These enrich beyond the raw schema descriptions.

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 states a specific verb ('hand... to'), resource ('local Codex CLI coding agent'), and scope ('can write and run code, install packages and call APIs'). It also distinguishes its output behavior from siblings by explaining it returns output plus created files, and routes async cases to codex_job_result.

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 gives clear when-to-use context and explicit guidance for the async case: if execution exceeds wait_sec, returns status:running and a job_id, and the agent is instructed to call codex_job_result. It does not explicitly contrast with codex_read_artifact or codex_generate_image, so it falls just short of full alternative differentiation.

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