fetch_outputs

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

With no annotations provided, the description carries full responsibility for disclosing behavior, and it does so thoroughly. It explains the url_only flag (emits URLs without downloading), the inline_images flag (returns base64 content while preserving on-disk copies), the return structure (metadata first, then capped image files), and the remote-job mechanism (state file keyed by prompt_id). It also discloses failure mode (download_job_not_found). No contradictions exist.

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 moderately long but every sentence adds critical information: the core action, wrapper command, remote handling, inline image behavior, and return caps. It is front-loaded with the primary purpose and then layers details. Slight verbosity is justified by the tool's complexity.

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 tool with no annotations and no output schema, the description covers all essential aspects: the return format (metadata first, then image files), the caps on inline images, the behavior for remote jobs, and the failure condition. It leaves no critical gap an agent would need to call the tool correctly.

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 description coverage is 0%, so the description must compensate. It explains the two optional flags (url_only and inline_images) with concrete behavior, and implicitly clarifies prompt_id and out_dir through the main sentence. The required parameters are self-explanatory, so the description adds value where needed without over-explaining.

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 opens with a clear, specific action: 'Download a completed job's output files into out_dir.' It names the verb, resource, and destination, and differentiates from sibling tools by specifying 'completed job' and wrapping the comfy download command. This leaves no ambiguity about what the tool accomplishes.

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 gives clear context on when the tool works, including for jobs run on a remote machine, and specifies a limitation: a prompt_id never submitted on this machine will fail. However, it does not explicitly contrast this with alternative tools (e.g., generic 'download' or 'download_model'), so the when-not-to-use guidance is implied rather than stated.

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