Draw Line

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 covered. The description adds only the targeting rule (most recent sketch) and says nothing about the non-idempotent implication that repeated identical calls create duplicate lines, whether constraints are auto-added, or what happens on failure. Beyond the annotation set, it contributes very little behavioral context for a mutating tool.

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 short sentence with zero filler and the target scope front-loaded. It is efficient, though the brevity is partly under-specification rather than disciplined compression.

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 6-parameter mutating geometry tool with no output schema and only 33% schema coverage, the description is too thin. An agent cannot learn from it what the coordinate system is, what the tool returns, or how errors (no sketch present) surface — all of which the description would need to carry given the absent output schema.

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 33%: start_z and end_z carry inline notes explaining they are ignored and that create_sketch(z_offset=...) should be used instead, but start_x, start_y, end_x, and end_y have no schema descriptions at all. The tool description does not compensate — it says nothing about coordinate units, origin, or that the coordinates are interpreted in the sketch plane, leaving the four required parameters semantically unexplained.

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?

"Draw a line in the most recent sketch" names a specific verb (draw) and resource (line) plus the target container (most recent sketch), which is concrete enough to act on. It does not differentiate from adjacent curve-drawing siblings such as draw_arc, draw_spline, or draw_rectangle beyond the geometry type itself, so it stops short of a 5.

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 phrase "in the most recent sketch" implicitly tells the agent the prerequisite context (a sketch must already exist and be the newest one) and implies that create_sketch should be called first. However, there is no explicit when-to-use statement, no named alternatives (draw_arc, draw_spline, draw_rectangle), and no stated behavior when no sketch exists.

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