Character Forge

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

Annotations indicate readOnlyHint=false (it's a mutating/generating action producing a cost) and openWorldHint=true (broad outputs). The description does mention the cost (25 MESH/call) and that it runs on serverless silicon, which adds useful operational context. However, it doesn't disclose behaviors like rate limits, GPU queue wait time, image size/resolution defaults, or what happens if the prompt fails content moderation.

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 compact and front-loaded with the purpose ('Generate an image'), then adds the differentiating detail (own GPU / FLUX / serverless silicon), the output promise (permanent image URL you own), and cost info. It's efficient at ~50 words with minimal filler, though the trailing tag 'a tool · media' and the playful 'not just the market' phrasing add minor noise.

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 openWorldHint=true and the generative nature of the tool, the description covers purpose, output format (permanent URL), cost, and compute location. However, with no output schema and no disclosed details about image dimensions, resolution, generation time, or moderation behavior on unsafe prompts, there are notable gaps an agent might need for reliable invocation and expectation-setting.

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?

With only 1 required parameter (prompt) and 100% schema description coverage, the schema already documents the prompt field clearly ('what to draw — describe the character or scene'). The description reinforces this by saying 'describe a character or scene'. There's minimal additional semantic value needed since the schema fully covers the single parameter; the description aligns with it.

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 generates an image on the mesh's own GPU using FLUX, from a text prompt describing a character or scene. The verb-resource pair (generate image / describe character) is specific. It doesn't explicitly distinguish from sibling cam-forge, but the FLUX/silicon detail and unique positioning make the purpose reasonably distinct.

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 tells the user to 'describe a character or scene' and implies this is a text-to-image generation tool. However, it does not give explicit when-to-use or when-not-to-use guidance versus alternatives like cam-forge, nor does it mention any input constraints such as prompt length, style guidance, or image aspect ratio to receive good results.

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