ai_backends

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

No annotations are provided, so the description carries the full burden. Its 'Which services are connected' framing implies a read-only discovery operation, and it discloses the categories of returned data (models, samplers, upscalers, workflows, avatars and voices when details=true). It says nothing explicitly about side effects, permissions, or cost, and does not describe the response shape.

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 sentences, front-loaded with the core purpose, and the actionable call-before-generate_image rule is placed last for emphasis. The long vendor enumerations are informative but slightly heavy; trimming them would lose useful completeness, so this is close to optimal.

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 and 0% schema coverage, the description must serve as documentation, and it does name the returned categories and the workspace workflows path. However, it does not describe the response structure (key names, per-backend shape, error when nothing is connected), leaving gaps for an agent that needs to consume the result.

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 0%, so the description must compensate for the single undocumented boolean. It does: 'details=true lists HeyGen avatars and voices' explains what the flag adds. It is incomplete because it does not say whether details affects other backends or what the default (false) yields, but it still adds real meaning beyond the bare boolean.

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 identifies the tool as a discovery query for connected generative-AI services, enumerating image backends, video backends, vision models, and ComfyUI workflows. It has no single leading verb like 'list' or 'get', but the enumerated scope distinguishes it well from siblings such as generate_image, generate_video, and ask_vision.

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 an explicit precondition: 'Call this before generate_image.' That is a concrete when-to-use rule tied to a named sibling. It does not mention generate_video or ask_vision, even though the tool also reports video backends and vision models, so the guidance is clear but not exhaustive.

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