add_rectangle

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

With no annotations provided, the description carries the behavioral disclosure burden. It does well by stating the outcome ('Add a rectangle'), the return value ('Returns line_indices for the 4 edges'), and the role of each point in each mode. It does not mention failure conditions, prerequisites, or side effects beyond the added geometry, which keeps it from a 5.

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 three compact sentences, with the main action and key parameters front-loaded. Each sentence earns its place: the first states purpose and kind values, the second gives the return value, and the third explains the point semantics per mode. No filler or repetition.

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?

For a geometry-creation tool with 5 parameters, no annotations, and no output schema, the description is reasonably complete. It explains all three construction modes, the return value, and the meaning of the coordinate parameters. It does not cover error scenarios, units, coordinate-space assumptions, or the requirement that the target sketch already exist, but it is adequate for selecting and likely invoking the 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?

Schema description coverage is 0%, so the description must compensate for the bare schema. It substantially does so by defining the meaning of p1, p2, and p3 for each rectangle kind, and by enumerating valid kind values. However, it does not explicitly state that p3 is only used when kind='3pt' or clarify whether p3 is semantically required for that mode, and 'sketch' is only implied as a target container.

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 and resource: 'Add a rectangle to a sketch.' It also identifies the three construction modes (center, corner, 3pt) and the return value, clearly distinguishing this from sibling tools like add_line and add_circle.

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?

It gives clear how-to guidance for each kind variant, explaining exactly how p1, p2, and p3 should be interpreted. However, it does not explicitly state when to prefer add_rectangle over a more general alternative like add_polygon, so it lacks explicit exclusion/alternative guidance.

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