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

Annotations cover safety profile (readOnly/idempotent), so description appropriately focuses on return value semantics ('evaluation dimensions, scoring criteria, and any user overrides') and cost ('Free'). Adds meaningful behavioral context beyond structured metadata.

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: purpose, return payload, parameter sourcing, and cost. Front-loaded with action and resource, efficiently structured for quick comprehension.

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?

Adequately complete for a single-parameter getter tool. Despite no output schema, description conceptually covers return contents. Combined with comprehensive annotations and full schema coverage, no critical gaps exist.

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 description coverage, the baseline is 3. The description reinforces the schema's sourcing guidance for model_id but does not add additional syntax, format details, or semantic nuances beyond what the schema already provides.

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 specific verb 'Get' with clear resource 'rubric for a custom eval model' and distinguishes from siblings by specifying it retrieves 'current' rubric including 'user overrides'—contrasting with atlas_infer_custom_eval_rubric (generation) and atlas_set/clear_custom_eval_rubric_overrides (mutation).

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 explicit sourcing guidance for the model_id parameter ('from atlas_create_custom_eval_model or atlas_list_custom_eval_models'), implying the workflow context. However, lacks explicit when-not-to-use guidance comparing retrieval vs. inference scenarios.

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