run_ruby

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

Annotations declare readOnlyHint=false and destructiveHint=true, and the description richly adds context: the whole snippet is one Undo step, returns the last value (inspect) plus puts output, and warns NOT to call start_operation/commit_operation because the bridge already wraps the code. This is exactly the behavioral detail annotations cannot convey.

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-loaded with purpose and the primary fallback condition, then dense, high-signal rules. It is long but virtually every sentence is actionable; only minor benefit from tighter grouping into explicit bullets.

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?

Covers purpose, safety profile, undo semantics, return values, unit conventions, entity lookup, and known API gotchas (face.normal before pushpull, local vertex coordinates). With no output schema, the description itself explains the return behavior, leaving nothing an agent needs to call it correctly.

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 0% for the single 'code' parameter, so the description must compensate. It does explain the semantics of the code content: internal units are inches (use 1000.mm, x.to_mm), end with a value or puts, and the value becomes the return. Strong compensation, though it doesn't formalize the parameter itself beyond content rules.

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 ('Run arbitrary Ruby code in SketchUp (Ruby API)') and immediately distinguishes itself from siblings with 'Use it when the other tools are not enough.' An agent can tell this is the escape-hatch tool without inspecting other schemas.

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?

Explicitly says to use it only when the other tools are not enough, effectively naming the alternative set and the condition that selects this one. Additional rules (find_entity_by_id, check face.normal, local vertex coordinates, no exit) give concrete invocation guidance.

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