eval_ruby

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

With no annotations provided, the description carries the full burden and excels. It discloses that only the last expression's .to_s is returned, stdout is not captured, errors are returned as '[code] message' with the Ruby exception class, and describes the gate-closed scenario including the JSON-RPC code and how the message is surfaced. This gives an agent a clear picture of what to expect before calling.

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?

The description is moderately long but every sentence adds essential detail: purpose, gating behavior, return value nuances, and error format. It is front-loaded with the core purpose in the first sentence and then expands on critical behavioral details. No fluff is present, but it could be tightened by reducing the explanation of the gate message wrapper, which is somewhat tangential to the core call.

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?

The description covers all critical aspects an agent needs to call it correctly: return format, stdout limitation, error handling, and the special gate-closed case. It also alerts the agent to the verbatim-message mechanism. For a single-parameter tool with an output schema (though not shown), this is complete enough for accurate invocation.

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?

The schema already describes the parameter with 100% coverage, so the baseline is 3. The description adds valuable usage guidance by advising to end scripts with an explicit expression like 'result.to_json' to obtain structured data, which directly affects how the parameter should be used. This elevates it above baseline.

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?

The description opens with 'Evaluate arbitrary Ruby code in SketchUp,' a specific verb and resource that unambiguously distinguishes it from all sibling tools which perform specific operations (create_layer, undo, get_version, etc.). There is no ambiguity about what the tool does.

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 does not explicitly contrast this tool with its siblings or state when to prefer it over other tools. It explains the gating behavior and error handling, but this is about behavioral context, not usage routing. The implied usage is as a general-purpose escape hatch for operations not covered by the specialized tools, but that is left to inference.

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