get_job

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 that completed runs trigger file downloads to disk, that 'saved_to' holds the local path and 'url' the public one in HTTP mode, that image results return as previews, and that wait_seconds is capped by COMFY_MAX_WAIT. It doesn't state error/retry behavior or whether repeated calls re-download, which keeps it shy of 5.

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 status states are front-loaded and the remaining sentences each add distinct behavior (downloads, URL modes, previews, wait cap). Slightly dense prose but no filler sentences.

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 covers return values well (saved_to, url, preview images) and the blocking semantics. The only gap is download_dir's purpose and default, which prevents a 5.

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 wait_seconds (blocking up to a cap, bounded by COMFY_MAX_WAIT) and implicitly ties downloads to download_dir, but prompt_id is never described and download_dir's null-default behavior is left to inference. Partial compensation for a 3-param tool.

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 opening sentence names the specific resource (a run/job) and its operation (reporting status), and enumerates the status states (queued | running | done | error), so the agent knows exactly what it gets back. It doesn't explicitly contrast with siblings like get_judged or run_workflow, keeping it at 4 rather than 5.

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?

Usage is implied: this is the polling/status-check tool you call after run_workflow, and wait_seconds suggests a blocking poll. However, there's no explicit statement of when to use this versus get_judged for judged runs, nor any prerequisite or exclusion guidance.

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