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

Beyond the annotations (which indicate it's a write operation), the description adds valuable behavioral context: the 'Free' cost disclosure, the base64 encoding requirement, file format constraints (PDF/DOCX), and the semantic meaning of quality labels (strong/weak/mixed). No contradiction with annotations exists.

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?

Every clause earns its place: action definition, format/encoding constraints, enum listings for artifact_type, enum listings plus semantics for label, model_id sourcing, and cost. Information is front-loaded and densely packed without redundancy.

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?

For a machine learning training-data upload tool, the description adequately covers prerequisites (model_id source), file constraints, cost, and labeling semantics. Given the lack of output schema, it appropriately focuses on input requirements, though it could briefly mention whether uploads trigger immediate processing or require separate training initiation.

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?

Despite 100% schema coverage (baseline 3), the description adds meaningful value by explaining what the 'label' parameter represents ('how this artifact exemplifies quality'), explicitly enumerating valid artifact_type values, and clarifying the base64 encoding requirement for the file parameter which aids correct invocation.

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 specific action (Upload), resource (file artifact), and purpose (to teach a custom eval model). It explicitly distinguishes this from sibling text-based tools by emphasizing 'file artifact' and specifying PDF/DOCX formats, while also listing the specific artifact types (CV, JD, template).

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?

It provides explicit guidance on obtaining the model_id parameter by referencing sibling tools (atlas_create_custom_eval_model or atlas_list_custom_eval_models). While it implies this is for file uploads versus text (contrasting with atlas_add_custom_eval_text_artifact), it could more explicitly state when to prefer this over the text-based alternative.

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