queue

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It thoroughly describes side effects (e.g., jobs receiving a NEW prompt_id when moved/edited), cancellation escalation with interrupt, VRAM freeing, and WEDGED reporting, and clarifies that partial results are discarded. It also distinguishes read-only actions ('list', 'get_workflow') from mutating ones, and explains the default omission of workflow payloads in list output.

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 structured as a bulleted list per action, front-loaded with a one-sentence purpose. It is appropriately sized given the tool's complexity (8 actions, multiple edge cases). While every sentence earns its place, the overall length is near the upper bound; a more condensed version could improve scannability without losing critical details.

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?

Despite having no output schema, the description covers return behaviors for key actions: status returns JSON booleans plus optional execution_stats and text_outputs, list returns prompt_id and position, and get_workflow returns the full payload. It also addresses the important edge case of text-preview nodes producing no image file, and directs users to get_history for full output filenames. The description is complete enough for an agent to use the tool effectively.

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 100%, so the baseline is 3. The description adds some contextual nuance (e.g., position defaults to back for edit, clear_pending recommended when resetting after a stuck render, include_workflows to keep output small), but most parameter meanings are already well-documented in the schema. The extra context is useful but not transformative beyond what the schema already conveys.

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 statement: 'Inspect and manage the ComfyUI execution queue.' It uses a specific verb ('inspect and manage') and resource ('execution queue'), and the action enum further distinguishes it from sibling tools like enqueue_workflow, get_history, and restart_comfyui. Each action is explicitly named and scoped, leaving no ambiguity about what the tool does.

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 provides explicit when-to-use guidance, e.g., 'Use this before action:"cancel"', 'Use action:"list" to see the whole queue at once, and get_history for full output filenames', and contrasts cancel vs cancel_queued vs clear. It also states exclusions like 'Running jobs cannot be moved' and 'Does not affect the currently running job', making it clear when not to use certain actions.

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