download_job_results

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 states the tool only resolves paths, that files are already written to ComfyUI's own output directory, and that nothing is copied. It doesn't cover behavior for incomplete or failed jobs, which is the main remaining gap.

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?

Two sentences, zero filler, and the core action is front-loaded ahead of the usage note and the no-copy clarification.

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 one-parameter read tool with no output schema and no annotations, the description covers the action, the precondition, and the return semantics (absolute paths, no copying). Missing only failure-mode guidance for jobs that aren't finished.

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 100% and the single prompt_id parameter is fully documented in the schema, including its origin from run_workflow. The description adds only the precondition that the job be completed, so the baseline 3 applies.

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 uses a specific verb and resource ("Resolve the native ComfyUI output file paths for a completed async job") and adds a disambiguating note that it only returns paths and copies nothing. It doesn't explicitly name the nearest sibling, get_job_result, so the distinction from that tool is left partly implicit.

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 triggering condition: use after run_workflow with wait_for_completion=false. There's no statement of when not to use it, nor a direct comparison to get_job_result or get_queue_status, so the agent must infer the boundary.

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