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

Annotations already establish the read-only, idempotent, non-destructive nature. The description adds valuable behavioral context not in the structured data: the specific return structure ('array of model objects with id, name, description, and status') and cost ('Free'). It appropriately compensates for the missing output schema.

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?

Four short sentences efficiently cover: (1) purpose, (2) return structure, (3) downstream usage, and (4) cost. Every sentence earns its place with no redundancy. Information is front-loaded with the core purpose.

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's simplicity (no parameters, read-only list operation) and absence of an output schema, the description is complete. It describes the return format, notes authentication requirements, explains how the results integrate with the broader tool ecosystem, and mentions cost—all essential for agent decision-making.

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?

The input schema contains zero parameters. Per the rubric, 0 params establishes a baseline of 4. The description correctly does not invent parameters, and the 'for the authenticated user' phrasing clarifies the implicit scope limitation without requiring explicit 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 explicitly states the specific verb 'List', the resource 'custom evaluation models', and the scope 'for the authenticated user' and 'all'. It clearly distinguishes this from siblings like atlas_get_custom_eval_model (singular retrieval) and atlas_create_custom_eval_model (creation) through the 'List all' phrasing.

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 post-retrieval usage guidance ('Use model id in artifact, rubric, and evaluation tools') and notes the cost ('Free'). While it doesn't explicitly contrast when to use this versus atlas_get_custom_eval_model, the zero-parameter nature and 'List all' phrasing make the use case clear.

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