comfy_batch

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

With no annotations, the description carries the full burden and does well: it discloses blocking semantics ('blocks until all are done'), a real side effect (local LLM is unloaded), the return content, and error/executor control via stop_on_error and keep_executor. It does not cover failure-partial-batch behavior or permissions.

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?

Purpose and return behavior are front-loaded in the first sentence, followed by a compact parameter reference. The dense inline-brace notation is efficient but slightly hard to parse; no sentence is wasted.

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 no annotations, the description supplies the return format (per-job status and output paths) and the key side effect, which is what an agent needs. Gaps remain around where output files land and what a partially failed batch looks like.

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% and the schema is bare (two untyped object properties), so the description must compensate fully — and it does, spelling out both job variants (workflow: kind/path/name; command: kind/command/cwd/timeout_s) and enumerating the options object's keys with inline meaning. This is far more than the schema provides.

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 names a specific verb and resource ('Run ComfyUI jobs on the GPU') plus the notable scoping condition ('while the local LLM is unloaded') and the return shape ('per-job status and output file paths'). An agent can tell this apart from voice_batch on the resource alone, though no sibling is named explicitly.

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 clear usage context: this is the path for GPU/ComfyUI work that must coexist with an unloaded local LLM, and the 'force' option signals the guard condition (another LLM server answering). It stops short of explicit when-not guidance or naming voice_batch/gate_status as alternatives.

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