GPT 原生生图 / 编辑（提交）

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.