sketch_pattern

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

With no annotations, the description carries the full burden and does well: it discloses atomicity ('all or nothing'), that counts include the original entity, and that the outcome differs by Fusion version (parametric with a constraint vs plain copies). It stops short of failure semantics or whether source entities are modified in place.

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?

One-line summary up front, then compact per-kind bullets, a type note, the return shape, and a single concrete example. Nothing is padding and the example earns its place by showing the circular case end-to-end.

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 12-parameter, no-output-schema tool, the description covers both modes, the value types, the parametric-vs-copy behavior, and returns {'instances', 'parametric', 'constraint'?, 'status', 'profiles'} plus the return_profiles speed tradeoff. Remaining gaps (error behavior, whether entities must lie in the target sketch) are modest.

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 already 92%, so the baseline is 3, but the description adds genuinely non-redundant meaning: 'counts include the original' clarifies count_x/count, spacing/angle accepts number = mm/deg vs string = expression, and angle for rectangular is measured from sketch X. That resolves ambiguity the schema alone leaves open.

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 ('Pattern sketch entities') and adds the key scope constraint 'all or nothing'. It does not explicitly contrast itself with the feature-level siblings pattern_rectangular / pattern_circular, so the sketch-vs-feature distinction rests on the tool name and the word 'sketch entities' rather than an explicit statement.

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 description lays out what each `kind` requires (rectangular: count_x ≥1, spacing_x, count_y=1, spacing_y=0, angle/direction; circular: center, count ≥2, angle=360), which tells the agent how to configure each mode. It never says when to pick this tool over pattern_rectangular or pattern_circular, nor any preconditions such as the sketch being active/editable, so usage context is implied rather than stated.

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