set_curve_property

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

The annotations include idempotentHint: true, which implies that repeated calls with the same inputs have the same effect; the description does not contradict this. However, the description provides no additional behavioral context: no mention of prerequisites (e.g., the object must be a curve), no mention of how the tool handles invalid properties or values, and no mention of side effects beyond what annotations cover. With annotations covering idempotency, the bar is lower, and the description is minimal but not misleading.

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 concise: it lists the properties in a single sentence, which is efficient for an agent to parse. It front-loads the action and the resource. The listing of properties is useful, and there is no wasted text. It is not overly verbose, so it earns a high score, though it could add more structural guidance.

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?

The tool has three parameters all required, no output schema (though context says has output schema true? Actually given output schema is true, but that's not in the tool description; the context signals say has output schema true, but the description doesn't mention return values). The complexity is moderate: setting a property requires understanding the value type for each property. The description lists properties but not their value constraints or examples. Given the low schema coverage and no usage guidance, the description is incomplete for an agent to correctly invoke the tool for all properties.

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%, meaning the input schema has no descriptions for 'object', 'property', or 'value'. The tool description partially compensates by listing valid property names, but it does not explain the format of 'value' (e.g., for dimensions, is it an array of floats?), nor does it clarify what 'object' refers to (e.g., object name or ID). The description must carry the full burden for parameter semantics, and it does not fully do so.

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 states a specific verb ('Set') and resource ('curve property'), and enumerates the properties it can set (bevel_depth, bevel_resolution, extrude, dimensions, resolution_u, fill_mode). This is clear enough for a basic understanding, but it does not differentiate from sibling tools like set_modifier_property or set_material_property, which are similarly named. The purpose is clear but not uniquely distinguishing in the context of many property-setting 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?

There is no guidance on when to use this tool versus alternatives. For example, there are siblings like create_curve, get_curve_info, set_curve_points, and convert_to_mesh, which all relate to curves, but the description does not mention when to use set_curve_property as opposed to those. Context is implied by the property names, but no explicit exclusions or alternatives are provided.

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