Get Training Data Documents

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

Annotations already declare readOnlyHint=true and destructiveHint=false, clearly indicating a safe read operation. The description adds no extra behavioral context (e.g., response size limits, pagination behavior). The bar is lower due to annotation coverage, so a central score is appropriate.

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, direct sentence with no unnecessary words. It front-loads the action and resource, making it easy to parse.

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 complete schema with parameter descriptions and annotations, the description together with the schema provides adequate context. It lacks an explicit mention of pagination via index/nValues or output format, but the schema covers that. The tool is straightforward (list retrieval) and the description is sufficient for a model with good annotations.

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% with descriptions for all 4 parameters. The description adds context by linking the parameters (type and id) to identify a model and its training data, which goes beyond the schema's individual parameter descriptions. For example, 'Get the documents used as training data for a model' clarifies that type+id together specify the model.

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 uses a specific verb 'Get' and identifies the resource as 'documents used as training data for a model.' This clearly distinguishes it from sibling tools like transkribus_model_get_train_data_stats (which returns statistics) and transkribus_model_get_validation_data_docs (validation vs training).

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 no guidance on when to use this tool or when to prefer alternatives. For example, it doesn't mention that this tool returns the actual document list while transkribus_model_get_train_data might return summary information, nor does it specify pagination usage via index and nValues.

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