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

Annotations already declare destructiveHint=true and idempotentHint=true. Description adds valuable behavioral context beyond annotations: explicitly states cascade effects ('removes... all associated artifacts and rubrics') and cost structure ('Free').

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 sentences with zero waste: action definition, destruction scope, parameter source, and cost. Front-loaded with the core verb and efficiently structured.

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?

Complete for a single-parameter destructive operation. Covers action, cascade impact, parameter sourcing, and cost. No output schema exists, so return value explanation is not expected.

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%, but description adds crucial provenance context for model_id ('from atlas_create_custom_eval_model or atlas_list_custom_eval_models'), guiding the agent on how to obtain valid values beyond just the numeric type.

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?

Specific verb 'Delete' + resource 'custom evaluation model' clearly defines scope. Distinguishes from siblings like atlas_update_custom_eval_model and atlas_create_custom_eval_model by explicitly referencing the latter as sources for the required parameter.

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 prerequisites by specifying that model_id comes from atlas_create_custom_eval_model or atlas_list_custom_eval_models. Lacks explicit 'when not to use' guidance (e.g., vs. updating), but the cascade warning implies permanent removal.

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