comfy_library

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

The annotations are empty, so the description carries the full burden of behavioral disclosure. It does share a return format and examples, but it does not disclose side effects of 'record', whether the operation mutates stored data, required permissions, or failure behavior. For a tool that includes a write-style operation, this is a significant gap.

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 compact and front-loaded: the purpose appears first, and the return format plus examples are genuinely useful. The main weakness is that 'record new ones' is vague enough that the opening sentence could be more precise. No obvious filler is present.

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 the tool has nine parameters and a multi-mode operation enum, the description is incomplete because it does not explain per-operation expectations, required parameter combinations, or behavior of the 'record' operation. The return format helps, but the description alone is not enough to correctly invoke all operations.

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 examples add some value by pairing operation values with relevant parameters, but the description still does not clarify which parameters are required for the 'record' operation or how fields like model, outputs, seed_val, prompt_id, and workflow_id interrelate.

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 names a clear domain: 'Browse past generations and record new ones', and the operation enum adds concrete verbs such as recent, search, and record. However, it does not differentiate this tool from siblings like show_generation_card or comfy_generate, and 'record new ones' is somewhat vague about what exactly is being recorded.

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?

Examples for 'recent' and 'search' show basic usage but there is no explicit guidance on when to use this tool versus alternatives, no exclusions, and no conditions for choosing record versus comfy_generate. The description leaves the agent to infer context from the operation enum alone.

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