annotation_auto_dimension

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

Annotations include destructiveHint=true, but the description does not elaborate on destructive behavior. It adds some context (performance rules) but does not explain side effects or state changes beyond annotations. No contradiction.

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?

Extremely concise: two sentences for core purpose and two performance rules. No redundancy, every sentence adds value.

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?

Despite having output schema and annotations, the description fails to explain the input parameters ('data', 'include_screenshot') or how to construct them. The catch-all 'data' parameter is left ambiguous, making the tool less usable.

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 description coverage is 0% for the two parameters ('data', 'include_screenshot'). The description references parameters like 'region', 'entity_ids', 'selection' that are not in the schema, and does not explain the actual parameters, leaving the agent uninformed.

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 tool's action ('plan and immediately commit dimensions') and resource ('one selected part/region/entity set'). It also distinguishes from sibling tools like annotation_batch_create_dimensions and annotation_plan_dimensions.

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 performance rules: when to use batch vs single, and how to optimize by passing region/entity_ids/selection and reusing geometry_cache_token after detect_parts. Explicitly states to avoid calling create_dimension_* repeatedly.

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