h3_check_backend

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

With no annotations, the description carries the full burden; it does convey that this is a non-mutating read ('Read ... status') and hints at an access constraint ('private'), which are the key safety signals. However, it never says what the status contains, whether it can fail or block work, or if auth is required — gaps that matter for a preflight gate with no output schema.

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 sentence, front-loaded with the action and resource, with the timing/precondition tagged on the end. Nothing is wasted and nothing needs to be trimmed.

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 zero-parameter read tool this covers the essentials of what it does and when, but with no output schema and no annotations the agent still cannot anticipate the response shape (backend up/down, queue depth, GPU availability) or how to interpret a failure. Adequate but with a clear residual gap.

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 takes zero parameters, so there is nothing for the description to disambiguate. Baseline score applies; the description correctly implies a no-argument invocation.

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?

States a specific verb ('Read') and resource ('ComfyUI system status'), and the qualifier 'private' plus 'backend' separates it from the job/generation siblings whose names all revolve around art jobs and video generation. It does not name a sibling to contrast with, but the purpose is unambiguous.

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?

'before submitting paid GPU work' gives a clear trigger condition for invoking it. It stops short of naming the specific alternatives (h3_art_generate, h3_generate) or stating when not to bother, so it is strong context rather than a full routing rule.

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