Draw Arc

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the safety profile is known; the description correctly does not contradict them. It adds the important behavioral detail that the arc is written into the most recent sketch rather than a newly created one, which matters for side effects. It does not cover what happens when no sketch exists, whether repeated calls stack arcs, or what the tool returns.

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?

A single front-loaded sentence with the action first and the required inputs in a compact parenthetical; nothing is redundant. It is arguably over-compressed for a 7-parameter mutation tool, but every word carries meaning and there is no filler.

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 non-idempotent geometry mutation with 7 parameters and no output schema, the description covers the essential shape of the call (center, start, sweep) but omits coordinate units, the prerequisite sketch state, and failure behavior. Because the schema already documents sweep_angle degrees/CCW and the ignored z parameters, the remaining gap is moderate rather than severe.

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 only 43%, and the undocumented parameters are the coordinate values (center_x/center_y, start_x/start_y) plus start_z/center_z. The description maps these to 'center' and 'start point', giving conceptual meaning and showing that center, start, and sweep fully define the arc. It adds no units for the coordinates and no plane semantics beyond what the schema's z-parameter notes already state, so it only partially compensates for the coverage gap.

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?

States a specific verb and resource ('Draw an arc') and enumerates the geometric inputs (center + start point + sweep angle), which cleanly separates it from draw_line, draw_circle, and draw_rectangle. It also names the target container, 'the most recent sketch', so an agent knows where the geometry lands. It does not explicitly distinguish itself from a spline or polygon tool, but the arc-specific construction is unambiguous.

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?

'In the most recent sketch' implies the prerequisite that a sketch must already exist and that this is a sketch-edit operation, but the guidance is implicit rather than stated. There is no instruction to call create_sketch first, no statement that an already-active sketch cannot be targeted, and no mention of alternatives or when-not-to-use. The agent must infer the workflow ordering from other tools.

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