compare_scenarios

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

Annotations indicate idempotentHint=true but readOnlyHint=false. The description does not clarify whether the tool modifies model state or only reports results. It mentions optional CSV output, a side effect, but lacks explicit statement on mutation. Dependency note adds context.

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 two sentences: the first efficiently conveys the core purpose and output, and the second adds a crucial dependency requirement. No redundant information, front-loaded with the action.

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?

Without an output schema, the description should detail the return structure more thoroughly. It mentions 'per-variable final/max absolute deltas and final percent change' but omits format, default behaviors (e.g., baseline default, include default), and performance considerations. This leaves gaps for an agent to infer.

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 100%, so descriptions are already in the schema. The tool description partly echoes schema fields (e.g., 'named what-if scenarios') but does not add substantial new meaning beyond schema defaults or behavior of optional parameters like model_id or 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 clearly states the tool runs named what-if scenarios against a baseline and reports per-variable deltas and percent changes. It specifies the action, input (scenarios and baseline), and output format, distinguishing it from sibling tools like simulate and sensitivity_analysis.

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 implies usage for comparing multiple parameter override sets to a baseline, but does not explicitly state when to use this tool vs alternatives like sensitivity_analysis or simulate. It mentions a required dependency, which is helpful but not usage guidance.

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