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

While annotations declare idempotentHint=true and readOnlyHint=false, the description adds valuable behavioral context: it discloses that the operation is 'Free' (cost transparency) and explicitly states the return value ('Returns the updated model object'), which is crucial given the lack of an output schema. No contradictions with annotations.

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?

The description is efficiently structured with zero waste: the first sentence establishes the core operation and scope, the second identifies the ID source, and the final two fragments concisely disclose return behavior and cost. Every statement earns its place 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?

Given the tool's complexity (updating evaluation models with nested dimension/weight objects) and lack of output schema, the description adequately covers the return object and cost. However, it could be improved by clarifying whether omitted fields result in partial updates versus requiring full object replacement, which is critical for a mutation tool.

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 schema already documents all five parameters. The description adds semantic grouping by categorizing the fields as 'metadata' and mapping them to the schema properties, but does not provide additional syntax guidance, examples, or constraint explanations beyond what the schema already supplies.

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 opens with a specific verb ('Update') and clearly identifies the resource ('custom evaluation model') and specific updatable fields ('name, description, inferred dimensions, weights'). It effectively distinguishes this from sibling tools like 'atlas_create_custom_eval_model' and 'atlas_list_custom_eval_models' through both naming and the explicit reference to retrieving model_id from those tools.

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?

The description provides clear prerequisite guidance by specifying that 'model_id' comes from 'atlas_create_custom_eval_model or atlas_list_custom_eval_models'. However, it lacks explicit guidance on when NOT to use this tool versus similar siblings like 'atlas_set_custom_eval_rubric_overrides' or 'atlas_clear_custom_eval_rubric_overrides'.

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