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

Annotations only state not read-only, not idempotent, and not destructive. The description adds valuable context: it saves to local storage, may consume quota, and does not auto-retry on failure. This goes beyond annotation data without contradicting it.

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 dense sentences: the first front-loads the core action and return values, the second covers model selection and important caveats about quota and retries. No wasted words.

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's mention of returned absolute path, actual dimensions, and PNG preview is essential and adequate. It also covers model default and failure behavior. Minor gaps remain, such as where the file is saved and overwrite behavior, but these are not critical for 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 coverage is 67% and two parameters already have schema descriptions. The description adds the default model (gpt-image-2.5-flare) and allowed alternatives, which is useful beyond the schema. However, it does not add meaning for the prompt parameter beyond what the schema implies.

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?

Description states a specific verb and resource: generate an image via CLIProxy's images/generations endpoint, save it locally, and return absolute path, actual dimensions, and PNG preview. This clearly distinguishes it from sibling tools list_models and generate_text.

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?

No explicit when-to-use guidance or alternatives are mentioned. The description explains how the tool behaves (default model, quota, retry policy) but does not tell the agent when to choose this over generate_text or list_models.

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 flag that the tool is not read-only and not idempotent, so the mutation profile is known. The description adds the genuine trait '调用可能消耗额度' (may consume quota), which is a cost/side-effect caveat beyond the structured data, plus the API-mode support. This is useful but modest context.

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 sentences with no filler; the purpose is front-loaded and the quota warning is appended efficiently. Every clause provides information that is not redundant with the annotations.

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 5-parameter tool with no output schema and 20% schema coverage, the description is too sparse. It omits parameter semantics, return format, error behavior, and any guidance on choosing api or system; an agent would have to guess or rely on external knowledge.

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 only 20%—only the 'model' parameter is described in the schema. The description adds no explanation of prompt, system, api, or maxTokens, so it fails to compensate for the uncovered parameters. The required prompt parameter is completely 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?

The description opens with '通过 CLIProxy 生成文本'—a specific verb (generate) and resource (text via CLIProxy). It also names the two supported API variants (Chat Completions and Responses), which clearly distinguishes it from sibling tools list_models and generate_image by semantic domain.

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 no explicit when-to-use or when-not-to-use guidance. The sibling tool names imply the distinction (text vs. image generation vs. model listing), but there is no statement about which tool to select for which task or when to avoid this one.

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 it read-only and open-world. The description adds value by specifying the list covers 'configured CLIProxy' models and by disclosing that a listed model may not support all interfaces. There is no contradiction with the readOnlyHint/openWorldHint annotations.

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 concise sentence states the core action and resource, followed by an important caveat. Every clause earns its place and the main purpose is front-loaded.

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 no-parameter read-only listing tool, the description is largely sufficient: it names the return content (model IDs) and an important limitation. It could be more complete by explicitly connecting the output to the generate_text/generate_image siblings, but the low complexity keeps the gap minor.

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 and the schema fully covers that with an empty properties object, so the baseline is 4. There are no parameter semantics for the description to enrich.

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 uses the specific verb '查询' (query) with resource '已配置 CLIProxy 的可用模型 ID', making it clear this tool lists configured model IDs. This distinguishes it from the sibling generation tools generate_text and generate_image, which produce content rather than enumerate 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?

The context implies list_models is used to discover model IDs before generation, but the description never explicitly says when to use it versus the siblings or that the IDs feed into generate_text/generate_image. The caveat about interface support hints at selection considerations, but it stops short of real usage guidance.

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