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

With no annotations, the description is the only source of behavioral info. It discloses the API endpoint and multipart format, and warns about a specific parameter conflict, adding value. However, it doesn't mention error handling, permissions, or output behavior beyond writing to output_path.

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 two sentences, reasonably concise and front-loaded with the main purpose. The warning about input_fidelity is valuable. Could be slightly more efficient by integrating the API endpoint into the first sentence, but no waste.

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?

Given 9 parameters, some complex (filename, output_path), the description doesn't provide additional context beyond the schema, which is quite detailed. The absence of output schema and annotations means the description does not clarify what the tool returns, but the schema covers most parameters. It's adequate but could hint at typical use cases or error scenarios.

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 parameter descriptions are thorough. The tool description adds minimal extra semantics beyond the schema, only noting that images are sent as repeated multipart field `image` (in schema) and the input_fidelity warning. It doesn't clarify relationships between parameters or edge cases beyond what's already in 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?

The description clearly states the tool edits or combines local images via a specific API endpoint and mentions a specific model. It distinguishes itself from generate_image and generate_gemini_image by focusing on image-to-image editing rather than generation. However, it doesn't explicitly name the alternative tools for clarity.

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 'Use for gpt-image-2 image-to-image', which provides clear context for when to use this tool, and warns against setting input_fidelity for gpt-image-2. It doesn't explicitly state when not to use it or mention alternatives, but the context implies generation tools are for other cases.

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 behavioral burden. It discloses the endpoint used (POST /v1/chat/completions) and the model family, which is useful. However, it doesn't disclose output behavior, file-writing semantics, or failure modes beyond the schema's filename notes. The description adds some context but not rich behavioral detail.

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, front-loaded with the core action and the critical endpoint exclusion. The second sentence is a clear directive. No wasted words, though it could have named sibling tools for extra routing value.

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 7 parameters, 100% schema coverage, and no output schema, the description is adequate but thin. It explains the endpoint and model family, but doesn't clarify when to prefer this over generate_image/edit_image, nor what the tool returns. The schema covers parameters, but the tool-level context is incomplete.

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 7 parameters. The description adds the endpoint context and the model-family constraint, but doesn't add parameter-level meaning beyond the schema. 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 ('Generate or edit images') and resource ('Gemini image model'), and explicitly distinguishes from the /v1/images/* endpoint family. It doesn't fully differentiate from sibling tools generate_image and edit_image, but the endpoint guidance and model family naming provide reasonable clarity.

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 an explicit 'Do not call /v1/images/* for Gemini image models' exclusion, which is a clear when-not-to-use signal. It doesn't name sibling tools generate_image or edit_image as alternatives, but the endpoint-level guidance is actionable and contextually useful.

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 full behavioral disclosure burden. It only states the endpoint and intended models, and does not disclose that the tool writes files to output_path, how overwrites or filenames behave, or what the response contains. Those details live in the schema, not in the behavioral description.

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 with no filler. The core action and endpoint are front-loaded, followed by the important routing guidance about Images-only models and the chat-completions exclusion.

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?

This is a 9-parameter tool with no annotations and no output schema, yet the description does not explain return values, file-writing behavior, or how it relates to edit_image. It is enough to identify the tool, but not enough to invoke it confidently without relying heavily on schema inspection.

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 baseline of 3 applies. The description adds no parameter-level meaning; all parameter semantics are already provided by the input 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?

The description names a specific operation (generate images), the exact endpoint (POST /v1/images/generations), and scopes which models it applies to (gpt-image-2 and other Images-only models). This clearly separates it from generate_gemini_image and edit_image.

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?

It gives a clear usage context: use for Images-only models, not for chat completions. It does not explicitly compare against the sibling image tools, but the model and endpoint guidance largely disambiguates when this tool should be selected.

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 mark readOnly=true and destructive=false; the description adds useful behavior beyond that by stating it is configuration-only, not live availability, and requires no network, credentials, or base URL. This gives an agent confidence that the call is safe and offline.

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 tightly packed sentences with no filler; the core purpose is stated first and the behavioral scope follows. 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, the description covers what the tool returns, what it does not include, and its execution context. No output schema or parameter details are needed for an agent to call this 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?

The tool has zero parameters, so the description cannot meaningfully add parameter-level detail. The baseline of 4 applies because there are no parameter semantics to document, and the description confirms the call takes no external inputs.

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 ('List'), a clear resource ('configured model groups and the tools that use them'), and immediately scopes the result to configuration only. This clearly distinguishes it from the image-generation siblings.

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 context: use it to inspect configuration, and it explicitly says it does not report live availability or use network, credentials, or base URL. It doesn't name an alternative because no sibling performs this function, but the guidance is otherwise sufficient.

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