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

Adds substantive semantics beyond the annotations: the cancellation is local-only, upstream execution may continue, no refund is guaranteed, and no retry is triggered. That is exactly the caveat an agent needs before a non-idempotent cancel; it only omits what happens if the job is already finished or unknown.

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?

One compact statement with the action front-loaded, then three semicolon-separated caveats. No filler at all; every clause carries a distinct constraint.

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 one-parameter, no-output-schema tool, the behavioral caveats cover most of what matters. The remaining gap is the identity of job_id, which the description should have sourced given the schema's zero coverage.

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 single required parameter job_id has 0% schema description coverage, so the schema supplies only 'string, minLength 1'. The description never mentions job_id, its format, or where to obtain it (e.g., from generate_gpt_image or get_image_job), leaving the parameter undocumented.

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?

Clear verb+resource: cancels a queued or running *local* image job, with the 'local' qualifier precisely scoping what is cancelled. It is distinguishable from siblings (get_image_job reads, generate_gpt_image creates) without naming them, but it makes no explicit sibling callout.

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 says what state a job must be in (queued or executing) to be a valid target, which implies when to call it. It does not state when not to use it, nor whether one should first verify status via get_image_job.

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?

Annotations already declare readOnly/idempotent/non-destructive, and the description adds valuable context beyond them: no quota is consumed, and a successful model listing does NOT prove image-generation permission. That caveat is exactly the kind of behavioral nuance annotations cannot convey. It falls short of 5 because there is no output schema and the description does not say what a result looks like or how to read a failure.

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, front-loaded sentences. The scope restriction ('仅 GET /models') comes first and the most important caveat about unverified generation permission closes it; no sentence is redundant.

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 zero-parameter, no-output-schema probe the description covers scope, side effects and the key interpretive limit. The remaining gap is what the response actually contains (model list vs. connectivity status) and how to interpret an error, which an agent would need to act on the result.

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; the schema is empty and fully covered, and no parameter semantics are needed or missing.

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 concretely that the tool performs only a GET /models call and never generates, which tells an agent this is a backend reachability/model-listing probe. It is clearly distinguishable from siblings generate_gpt_image, get_image_job and cancel_image_job, though the action verb itself is implied by the HTTP call rather than named.

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?

'真实生图必须另行调用' explicitly routes actual generation to another call, and the description establishes this as the read-only pre-check. It gives clear context for use but does not spell out positive triggers (e.g. when to run it before generate_gpt_image) or failure handling.

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?

Annotations already declare a non-read-only, open-world, non-idempotent operation, and the description adds genuinely new behavior: submission returns a job_id immediately (asynchronous), success must be confirmed via get_image_job, reference images are uploaded to the configured upstream proxy, quota may be consumed, and no automatic retry occurs. These are exactly the traits an agent needs and none of them are in the structured fields.

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?

Four short sentences, front-loaded with what the tool is and immediately followed by the mandatory polling step; nothing is padding. Density is high and the final sentence packs three distinct caveats (local-only references, quota, no retry), which is efficient though slightly terse for the amount of information carried.

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 7-parameter async generation tool with annotations but no output schema, the description covers lifecycle (job_id, polling), cost, retry policy, and reference-image handling — the parts an agent cannot infer. Minor gaps remain around the semantics of size/quality/output_format and where files land, though output_path is partially covered by the schema.

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 57%, and the description meaningfully supplements reference_images (user-explicit local files only, uploaded upstream) — a privacy/scope constraint the schema does not convey. However, size, quality, output_format, output_path, and filename_prefix get no added meaning, so roughly half the parameters remain documented only by 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?

Names a specific verb and resource — GPT native image generation/editing via the configured OpenCodex Responses image_generation path — and explicitly excludes the WorkBuddy built-in model path, which separates it from other image routes. It also names the follow-up sibling get_image_job, so an agent can place it in the workflow without opening any schema.

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 operating conditions: submit, then poll get_image_job until completed before claiming success; reference images must be user-specified local files; quota may be consumed and there is no auto-retry. It stops short of stating when to prefer this tool over check_image_backend or any other sibling, so the exclusions are implicit rather than enumerated.

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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description still adds real value: on completion it returns actual image paths/dimensions plus a standard MCP image block, and it explicitly guarantees failures are never reported as success. It stops short of describing the still-pending outcome after wait_seconds elapses.

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 clauses separated by a semicolon, with the lookup/wait behavior front-loaded and the return/failure contract second. No filler, no restatement of the title.

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 carries the return-value burden and does so for the success and failure cases (paths, dimensions, image block, no false success). The notable omission is what is returned when the job is still pending after the bounded wait, which is the central ambiguity for a polling tool.

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% and the two documented params (wait_seconds, include_preview) already carry good inline descriptions. The tool description only restates the job_id lookup and the bounded wait, adding no format or default detail beyond the schema, so the baseline 3 fits.

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+resource pair ('按 job_id 查询或有界等待' on an image job) and makes clear this is the retrieval step, implicitly distinct from generate/cancel siblings. It never names a sibling tool explicitly, so the differentiation relies on the agent's inference.

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?

'有界等待' signals that polling with a bounded wait is the intended pattern, but there is no explicit guidance on when to call this versus generate_gpt_image or cancel_image_job, nor when to re-poll after a pending result. Usage is implied rather than stated.

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