get_batch_output

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

With no annotations, the description carries full burden. It discloses that the tool returns raw ComfyUI history outputs, filenames feedable to get_image, and lists states for pending/errored jobs. It also explicitly states safety of early calls. This provides good behavioral insight beyond the schema.

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 a single paragraph of about four sentences, front-loading the purpose. It is efficient and free of fluff, though could be slightly more structured with bullet points for different job states.

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?

Given no output schema and moderate complexity (handling multiple job states), the description adequately explains what is returned for each state, references related tools (get_history, get_image), and specifies the data structure. It covers essential information for an agent to use 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 coverage is 100% for the single parameter batch_id, described as returned by submit_batch. The description does not add additional meaning beyond this, so baseline 3 is appropriate.

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 clearly states the tool collects outputs for a batch's COMPLETED jobs, detailing the data returned for done prompt_ids and states for pending/errored jobs. While the verb 'collect' is somewhat generic, the resource and scope are specific enough to distinguish from siblings like get_batch_status.

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 implies usage context by noting it's 'Safe to call before the batch finishes' and distinguishes completed vs. pending/errored jobs. However, it does not explicitly state when not to use this tool or compare it to alternatives like get_batch_status or wait_for_batch.

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