sensitivity_analysis

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the sweep mechanism, the recomputation of rankings, and the specific outputs (robustness score, critical criteria, flip points). It does not mention side effects or prerequisites explicitly, but the read-only analysis nature is implied.

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 only two sentences, front-loaded with the core purpose, and includes specific details about defaults and outputs without any redundancy. Every sentence contributes substantive information, making it highly concise and effective.

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 provides a clear overview of the tool's function, process, and outputs, which is sufficient for an agent to understand its role. It lacks explicit mention of prerequisites (e.g., needing a prior decision with weights and scores) and does not specify how to interpret the robustness score, but the description covers the essential behavior.

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 description explicitly explains 'variation' and 'steps' with defaults, adding meaning beyond the schema. However, it does not mention the 'method' parameter or clarify how options/criteria/scores are used beyond what the schema already describes. With 50% schema coverage, the description only partially compensates for undocumented parameters.

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 starts with a specific verb-resource pairing: 'Test how robust the winner is to criteria-weight changes.' This clearly distinguishes it from sibling tools like score_options or compare_two, which focus on scoring or pairwise comparison. The method details further reinforce its unique purpose.

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 clearly implies its use case: testing robustness after a winner has been determined. It provides clear context for when to invoke this tool but does not explicitly name alternatives or exclusions. Since siblings like compare_two and score_options exist, a direct alternative would improve it, but the purpose is self-explanatory.

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