create_pattern

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

With no annotations provided, the description carries the full disclosure burden and does it well: it flags mutation ('May change scene or write files'), demands state verification ('Verify resulting state'), and states non-obvious timeout semantics ('A timed-out operation is UNKNOWN: reconcile_operation before any retry'). It stops short of a 5 because it doesn't hint at what 'verify' entails or what failure modes other than timeout look like.

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?

Roughly 50 words across four sentences, with the core action and format front-loaded before safety and timeout notes. The only waste is redundancy: 'Verify resulting pattern' and 'Verify resulting state' express nearly the same instruction in consecutive sentences.

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?

Given no annotations and no output schema, the description covers the highest-stakes facts well: point format, side effects, verification requirement, and timeout handling. However, it leaves three gaps an agent would hit: what 'name' does, what the tool returns on success (no output schema to fall back on), and whether this appends vertices to an existing pattern or creates a new one. Solid for the essentials, incomplete on the edges.

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 coverage is 0%, so the description must compensate. It fully documents the critical 'points' parameter structure — each element is [x_mm, y_mm, type] with type meaning explained — which the raw schema (array of arrays of numbers) entirely fails to convey. The optional 'name' parameter is never mentioned, preventing a 5.

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 ('Create [x_mm,y_mm,type] vertices') with the type encoding spelled out (0=straight, 2=spline, 3=Bezier). This is distinguishable from the sibling family (list_patterns, get_pattern_points, move_pattern_point, delete_pattern). Minor ambiguity remains about whether this creates a new pattern object or adds vertices to an existing one, given the tool name says 'pattern' but the description only mentions vertices.

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?

No guidance on when to use this tool versus alternatives among the many pattern/sewing siblings. The only usage-adjacent guidance is operational — 'Verify resulting pattern' and 'reconcile_operation before any retry' — which addresses post-call behavior, not tool selection. An agent gets no help deciding between create_pattern, create_sewing, or move_pattern_point.

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