Train Table Recognition

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

The description adds little beyond the annotations. 'Start training' implies a non-read-only, non-destructive action, aligning with annotations, but fails to disclose that training is an asynchronous job that may consume credits, return a job ID, or have constraints. The openWorldHint annotation suggests broad applicability, but the description provides no additional behavioral context.

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 sentence with no wasted words, but it is overly brief. It could include additional context (e.g., 'Returns a job ID') without sacrificing conciseness. The front-loading is adequate, but depth is lacking.

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?

No output schema is provided, and the description does not specify return values (e.g., job ID or status). Given that the tool starts a training process (likely asynchronous), the agent needs to know what to expect back. The two required parameters (collId and config) are mentioned, but the config object's complexity (nested object) is unaddressed. The description is incomplete for an AI agent to use confidently.

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%—both parameters (collId and config) have descriptions in the schema. The description adds no extra meaning; it repeats 'collection' but does not explain the config object's structure or expected keys. Baseline score of 3 is appropriate as schema already documents parameters.

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 action ('start') and resource ('table recognition model training') with scope ('for a collection'), effectively distinguishing it from inference tools like transkribus_la_table_inference and other training tasks. However, it does not clarify what a 'collection' is in the Transkribus context, slightly limiting precision.

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?

There is no guidance on when to use this tool versus alternatives such as transkribus_recog_train_htr_citlab or transkribus_recog_train_la2. No prerequisites, preconditions, or exclusions are mentioned, leaving the user to infer the appropriate use case from the tool name alone.

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