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

Adds substantial context beyond the annotations (openWorldHint, destructiveHint=false): billing to the user's ChatGPT/Codex plan with no API key, files copied into out_dir, previews returned for verification, transparent/reference-image support, and a 30-120 s latency expectation. The latency and billing disclosures are exactly the behavioral traits an agent needs.

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?

Five tight sentences, front-loaded with what the tool is and the billing model, then capabilities, then latency. No filler and every sentence carries distinct 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?

Covers purpose, cost, output location, previews, capabilities and timing for an 11-param tool. It stops short of explaining the async/job_id behavior implied by wait_seconds, which matters with no output schema, but otherwise the agent has enough to invoke it correctly.

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 the schema already documents all 11 parameters thoroughly; baseline is 3. The description reinforces a few (out_dir copying, transparent backgrounds, reference images) but adds no syntax or format detail beyond the schema text.

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 verb+resource ('Generate image assets') and names the underlying mechanism (Codex's built-in image_gen / GPT Image), which clearly separates it from siblings like codex_job, codex_task, and codex_models.

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 use cases ('icons, sprites, illustrations, textures, UI mockups and similar'), so the agent knows when this tool applies. However, it never names an alternative or states when NOT to use it (e.g. vs codex_task), so routing guidance is clear but incomplete.

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 must carry the behavioral burden; it does disclose three distinct modes (block waiting, plain fetch, cancel), which is real behavioral content. It omits whether cancel is destructive or irreversible, whether waiting blocks the agent, and any permission or rate-limit constraints.

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?

A single sentence covering all three operating modes with no filler; the fetch/result framing is front-loaded. Slightly compressed in a way that blurs the distinction between the three modes.

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?

With no output schema and no annotations, the description should say what a result actually looks like and what happens when the job is not yet complete. It only hints at this indirectly via the schema's wait_seconds ('returning a job_id'), and is silent on cancel permanence.

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 67%: cancel and wait_seconds are documented in the schema with meaning and range. The description adds value by clarifying that job_id originates from a codex_task or codex_image job, but it adds nothing about cancel semantics or wait behavior beyond what the schema says.

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 verb set (wait for / fetch / cancel) and the resource (a codex_task or codex_image job), so an agent understands it acts on job results rather than creating them. It does not distinguish itself from the sibling codex_jobs, leaving ambiguity about which of the two to call.

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?

By naming codex_task / codex_image as the job producers, it implies this is the follow-up call that retrieves or cancels their output. However, there is no explicit when-to-use vs codex_jobs, no statement of preconditions, and no guidance on choosing wait vs fetch vs cancel.

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?

The readOnlyHint=true annotation already establishes this is a safe read. The description adds useful scoping ('started by this server') and discloses the shape of each returned row (status, kind, session_id), which the annotations do not cover. However, it says nothing about how 'recent' is bounded, ordering, or result limits.

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?

A single front-loaded sentence with the verb and scope first and the returned fields in a compact parenthetical. Nothing is wasted, though the parenthetical field list is thin enough that it barely earns its space.

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?

With no output schema, the description usefully compensates by naming the fields in each row, and the zero-parameter schema means there is no input surface to document. The main remaining gap is the absence of any bound on 'recent' (count, window, or pagination), which an agent would want before calling.

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 tool takes zero parameters, so the baseline is 4. There is no parameter surface for the description to clarify or omit, and it correctly does not invent any.

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 verb ('List') and resource ('recent jobs started by this server'), and even names the fields returned (status, kind, session_id). It is clearly distinguishable from the singular codex_job sibling, but the description never explicitly names that sibling or the boundary between them.

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 phrase 'recent jobs started by this server' implies a browsing use case, but there is no explicit when-to-use statement, no when-not, and no reference to codex_job for retrieving a single job's details. The agent must infer the routing itself.

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?

readOnlyHint=true already declares the safety profile, so the bar is lower. The description still adds real context: the data comes from both the user's account and the configured default in config.toml, and it names what each entry contains. It omits anything about ordering or result size, but for a small enumeration that is minor.

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, both earning their place: the first defines the output, the second gives the call trigger. No redundancy 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?

With no output schema present, the description carries the return-value burden and does so by listing the fields returned and where the default comes from. Combined with the explicit usage trigger, an agent has everything needed to invoke it correctly.

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?

Only one parameter and schema description coverage is 100%, so the schema fully documents include_hidden. The description says nothing about it, adding no meaning beyond structured data, which is the baseline-3 case.

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?

Specific verb (List) + resource (Codex models) scoped to the user's account, and it enumerates the returned fields (slug, description, reasoning efforts, default effort) plus the config.toml default. Siblings (codex_job, codex_task, codex_image, codex_jobs) are plainly different resources, so no confusion arises.

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?

Explicitly states when to call it: 'Use before choosing `model` / `reasoning_effort`.' That gives a clear triggering condition. It does not name an alternative tool or an exclusion case, so it stops short of a 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?

Adds substantial context beyond the destructiveHint/openWorldHint annotations: it runs locally with the user's own subscription, executes `codex exec`, works in `cwd`, can edit files there under workspace-write, and describes both return shapes (final message + session_id, or a job_id when it overruns wait_seconds). This is exactly the behavioral depth an agent needs before invoking a file-mutating local 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?

Front-loads what the tool is and where it runs, then use cases, then prompt guidance, then return/job behavior. Every sentence carries information; 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 10-parameter local execution tool with no output schema, the description covers the execution model, file-edit semantics, prompt construction, session continuation, and the async job_id fallback. An agent can invoke it correctly and handle both result shapes without further context.

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 real meaning: it explains how to compose `prompt` (goal, relevant files, constraints, what to report back) and connects `sandbox`, `cwd`, `session_id`, and the job_id flow. This goes beyond restating the schema.

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 (delegate a task to OpenAI Codex via `codex exec`) and the resource/context it operates on (this computer, the user's subscription). It also implicitly distinguishes itself from the polling sibling by noting that long runs return a job_id handled by codex_job.

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 use cases (second opinion, code review, well-scoped change, refactors, tests, codebase digging) and routes the agent to codex_job for waiting tasks and to codex_models for model slugs. It lacks explicit when-not-to-use guidance but the positive routing is clear.

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