text_to_image

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool returns a task id, status, and output URLs, and mentions 'task' semantics (implying async operation), but does not disclose the wait/polling behavior, rate limits, cost implications, or reversibility. For a task-based image generation tool with zero annotations, more behavioral context is expected.

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 a single clear sentence that establishes purpose and return value in under 30 words. It is front-loaded with the key information (what it does, what it returns). While it could add usage guidance, for conciseness and structure this is appropriately sized and efficiently worded with zero 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?

The tool has 9 parameters, no output schema, and no annotations, making it fairly complex. The description explains the task-based async model and return payload shape (task id, status, URLs), which is helpful context. However, it doesn't clarify the relationship between wait/poll_interval_ms/timeout_ms/callback_url parameters or when async vs sync operation is preferred. For a tool with this many configurable async behaviors, more contextual guidance would be valuable.

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 78%, which is above the 80% baseline... actually at 78%. The description adds 'Returns a task id, status, and output URLs' framing but does not explain individual parameters beyond what the schema already provides. Parameters like timeout_ms, poll_interval_ms, and callback_url are self-explanatory in schema but the description's task-based framing adds marginal context about how they relate to each other. The description compensates slightly but doesn't deeply enrich parameter semantics.

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+resource: 'Create a Qwen Image task on RunAPI (text to image)'. It clearly indicates the tool generates an image from text and returns a task id, status, and output URLs. It differentiates from siblings (edit_image, remix_image) by specifying 'text to image' generation, though it could be more explicit about distinguishing itself from the editing/remix 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 indicates this tool creates a text-to-image task with optional wait behavior, but does not explicitly say when to use this vs edit_image or remix_image, nor when to use the wait parameter vs callback_url. The schema implies polling capabilities but the description doesn't provide clear guidance on selecting this tool over siblings or choosing among the async patterns (wait, callback_url).

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