pattern_path

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

With no annotations, the description carries the full burden and does so well: it names the specific error codes (INVALID_PARAMS, FUSION_API_ERROR), the conditions that trigger them (mixed kinds, mixed curves/edges path, start outside 0..1, gaps), and the state outcome in each case ('nothing changed', 'rolled back'). It also documents default units and the start-as-share semantics.

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?

Front-loads the one-line purpose, then segments Units/Refs/Errors/Returns/Example so each labeled line is scannable and non-redundant. The example call at the end is compact and earns its place by showing argument wiring.

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 mutation tool with no output schema, the description supplies the return keys, the failure modes and their atomicity guarantees, and a worked example. Nothing an agent needs to invoke it safely is missing.

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 already 100%, so the baseline is 3. The description adds genuine meaning beyond it: units default to mm or accept an expression, start is a share of path length, and refs must be sourced from sketch_* results or inspect_query. It does not cover several non-obvious params (compute, distance_type, path_chain, symmetric), keeping it at 4.

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 with the distinguishing mechanism: 'copy features, bodies, faces or occurrences along a path of sketch curves or edges.' The path-based copying contrasts naturally with the sibling pattern_rectangular/pattern_circular, so an agent can pick it without opening a schema.

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?

Gives concrete selection context: what can be patterned, where refs come from (sketch_* results, inspect_query), and the constraint that all entities must be of one kind. It does not explicitly name sibling alternatives or state when not to use it, so it stays below 5.

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