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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the mutation and external-call profile is known. The description adds real value with "Results are saved to disk" and the mask transparency semantics, but says nothing about cost, latency, moderation implications, or whether returned file paths are handed back to the agent.

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 short sentences, front-loaded with purpose, then the optional mask caveat, then the output side effect. Nothing is padded and nothing is buried.

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 15-parameter tool with no output schema, the description covers purpose, mask behavior, and where files land, but omits what the tool actually returns (paths? inline images? count?) and how to choose between models or sizes. The rich schema carries most of the weight, leaving the description adequate but thin for this complexity.

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% and every one of the 15 parameters is already documented in the schema, so the baseline is 3. The one genuine addition is the mask rule ("transparent pixels mark the area to change"), which explains effect rather than just format, but the remaining parameters (model, size, quality, n) get no guidance in the description beyond what the schema states.

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 and resource ("Edit or combine existing images") and reinforces it with a concrete multi-image example, which clearly signals it operates on existing inputs rather than generating from nothing. It never names generate_image as the contrast case, so the split between the two siblings is left implicit rather than stated.

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 composite example ("put the product from image 1 on the background from image 2") illustrates one usage pattern, implying when to reach for this tool. However there is no explicit when-not, no prerequisites (API credentials, cost, latency), and no statement of how this differs from generate_image despite it being the obvious alternative.

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 description adds meaningful behavior beyond the annotations by noting that images are saved to disk and their paths returned. However, with readOnlyHint=false and openWorldHint=true already flagging a write operation, it does not disclose overwrite behavior, permissions, cost, or rate-limit implications.

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 short sentences with no wasted text: the purpose is front-loaded, then model choice, then output behavior. Every sentence contributes useful 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?

For a 12-parameter write tool with no output schema, the description covers the core purpose and notes that images are saved and paths returned. The schema handles parameter details. Minor gaps like overwrite behavior and cost are not critical to invoking the tool 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 all parameters are already documented in the schema. The description adds only 'Choose the model per call,' which is already covered by the model parameter description, 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 states a specific verb and resource: generate images from a text prompt via the OpenAI Images API. It is clear about what the tool does, though it does not explicitly distinguish itself from the sibling edit_image tool beyond the name difference.

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?

Usage is implied by 'Generate images from a text prompt' and 'Choose the model per call,' but there is no explicit guidance on when to use this tool versus edit_image or when not to use it. Alternatives are not mentioned.

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 description's added value is its disclosure of the payload contents (capabilities, default model, retired models) — meaningful since no output schema exists. It omits any mention of ordering, auth requirements, or whether retired models are flagged as unusable, keeping it short of a 5.

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 that conveys the action, the resource, and the return contents with no filler. Every clause 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 zero-parameter, read-only tool with no output schema, the description covers the essentials: what is returned and that it includes the default and retired models. Minor gaps (e.g., whether retired models are marked deprecated or excluded from use) are unlikely to block a correct call.

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, which is the baseline-4 case; there is nothing for the description to disambiguate. The description correctly signals a no-argument call by not implying any filtering or selection options.

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 pairs a specific verb ("List") with a specific resource ("supported OpenAI image models") and enumerates what the listing contains: capabilities, the default model, and retired models. It does not explicitly name generate_image/edit_image, but the read-only "list" verb is self-evidently distinct from the sibling generation/editing tools.

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?

Usage is only implied: an agent can infer this is the discovery step before calling generate_image or edit_image. There is no explicit statement of when to call it, when not to, or a named alternative, so it sits at the minimum-viable level for guidance.

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