Create AI images from text prompts for social posts, then use the returned URL in media upload or post creation workflows. Costs 1 AI credit per image.
Generate an image with AI (DALL-E) for use in posts. Costs 1 AI credit. Returns the image URL — pass it through upload_media/create_post media flow.
| Name | Required | Description | Default |
|---|---|---|---|
| style | No | Style hint (e.g. 'photorealistic', 'illustration') | |
| width | No | ||
| height | No | ||
| prompt | Yes | What to generate (≤4000 chars) |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare the generic profile (not read-only, not destructive, not idempotent); the description adds the genuinely useful facts: it consumes 1 AI credit and returns an image URL that must be routed onward. That credit cost is the key operational signal for a non-idempotent call and is not recoverable from the annotations. It stops short of covering failure behavior or whether credits are charged on a failed generation.
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, front-loaded sentences with no filler: capability, cost, then return-and-route. The final clause ("pass it through upload_media/create_post media flow") is slightly telegraphic but still parses correctly.
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 correctly carries the return value (an image URL), and it discloses the credit cost. The remaining gap is dimensional parameters plus any statement of size limits or defaults, which matters for a tool that silently accepts width/height.
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 only 50%: prompt and style are documented in the schema, but width and height have no description at all. The description adds nothing about these — no units (pixels), no defaults, no aspect-ratio or model-limit guidance — so an agent has to guess at valid values for two of four parameters.
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?
"Generate an image with AI (DALL-E)" names a specific verb and resource, and "for use in posts" scopes it against image-adjacent siblings like generate_carousel, render_carousel, and create_video without ambiguity. An agent can tell immediately what this produces.
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 downstream routing instruction — pass the returned URL through upload_media/create_post media flow — which effectively tells the agent this is a generation step, not a publish step. It lacks an explicit when-not-to-use clause (e.g. versus generate_carousel for multi-image assets or upload_media for existing files).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.