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

Annotations already establish the safety profile (non-readOnly, non-destructive). The description adds valuable behavioral context that the operation is 'Free' (cost). However, it omits whether adding an artifact triggers immediate model retraining, queuing behavior, or persistence details.

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?

Efficiently structured with the core action front-loaded. Each sentence delivers distinct value (purpose, use cases, parameter enum values, cross-references, cost). The enum lists are slightly redundant with schema coverage but aid quick scanning.

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 100% schema coverage, present annotations, and lack of output schema, the description is appropriately complete. It covers the operation purpose, parameter semantics, data sources, and cost. Absence of return value documentation is acceptable given no output schema is defined.

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?

With 100% schema coverage, the baseline is 3. The description adds significant value by explaining semantic context for text_content ('rubric notes, evaluation criteria text') and explicitly stating that model_id should be sourced from specific sibling tools, aiding the agent in chaining calls correctly.

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 ('Add'), resource ('plain text artifact'), and purpose ('teach a custom eval model'). It effectively distinguishes from sibling tool atlas_upload_custom_eval_artifact by emphasizing 'plain text' and 'free-form descriptions' versus file uploads.

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?

Provides clear positive usage guidance ('Use for free-form descriptions...rubric notes') and explicitly references sibling tools atlas_create_custom_eval_model and atlas_list_custom_eval_models for sourcing the model_id parameter. Lacks explicit negative guidance (when not to use vs alternatives).

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