job

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

With no annotations provided, the description carries the full burden and excels: it discloses that error returns None when healthy, that wait's timeout is a non-failure signal, that watch may return null progress due to comfy-cli 1.15.0 limitations, the error_code naming scheme for crashes, and the node_failure vs server_died distinction. This is exemplary behavioral disclosure.

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 long, but its density is justified by the multi-action surface — each of six actions earns its dedicated block with behavior and edge cases. The opening line front-loads the overall purpose, and formatting with bulleted actions aids scannability. Minor redundancy (defaults repeated) keeps it from a 5.

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 complex multi-action tool with no output schema and no annotations, the description covers everything needed to call it correctly: parameter requirements, per-action return shapes (timed_out dict, status snapshots, error fields), timeouts, ceilings, and version caveats. Nothing an agent needs to invoke it correctly is missing.

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%, but the description fully compensates: it enumerates every valid action value for the 'action' parameter with its effect, clarifies that prompt_id is required for all actions except 'queue', and specifies timeout_seconds applies only to 'wait'/'watch' — even noting that unused params are rejected. This exceeds what the bare schema would convey.

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?

Description states a specific family of verbs (Inspect, wait on, watch, cancel) applied to a clear resource (submitted job), plus the 'one action per call' constraint. It maps six distinct actions to underlying CLI commands, making the tool's scope unambiguous and distinguishable from the workflow/launch siblings in context.

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 instructs when each action is appropriate: 'safe to call speculatively' for error, wait vs watch polling behaviors with defaults/ceilings, and crash handling that points to a sibling ('check get_logs before relaunching'). It lacks explicit 'use X instead of this' exclusions, but the get_logs referral and per-action semantics give clear contextual guidance.

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