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

Annotations already declare this is a non-readOnly, non-destructive, non-idempotent mutation, so the safety bar is partly met. The description adds useful context about the user-approval tradeoff of the upload path, but omits what object is actually created, which artboard it lands on, whether repeated calls duplicate, and what a name/style_ref resolves to.

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?

Two sentences, purpose front-loaded, no filler. The second sentence is dense but every clause (JSON file, curl to upload link, pass only upload_id, fields in the call win) carries actionable information.

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 14-parameter, zero-required, deeply nested creation tool with no output schema and low schema coverage, the description should at least establish the coordinate model, default behavior with no points, and what is returned. Instead it covers only the upload shortcut, leaving an agent unable to call it confidently without reading the schema repeatedly.

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 14% across 14 parameters with nested objects. "Anchors with optional absolute handles" glosses points/hin/hout, but tension, tension_in/out, tangent, smooth, subpaths, closed, mirror, corner_angle, fill_handles, style, and artboard are left entirely to the field names — a large gap the description does not close.

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 one path from anchors with optional absolute handles" gives a specific verb and resource plus the core mental model (anchors + handles). "One path" implicitly distinguishes it from batch siblings like create_shapes or draw_svg, but it never names them, so the agent must infer the boundary itself.

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 second sentence gives a concrete workflow rule (use upload_id when a shell is available so the approval box stays short), which is real usage guidance. However it says nothing about when to choose create_path over edit_path, pencil, draw_svg, or offset_path — the sibling set is dense and no routing is offered.

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