sensitivity_analysis

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

Annotations declare idempotentHint=true, and the description adds context: requires optional pysd dependency and can optionally write CSV (save_sweep_csv). No contradictions with annotations. It could mention whether it modifies model state, but the computational nature is clear.

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?

Two sentences, no wasted words. First sentence front-loads the core functionality and outputs. Second sentence adds essential dependency note. Highly efficient.

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?

Given complexity (7 params, nested objects, no output schema), the description explains the OAT method and mentions outputs (slope, elasticity) but lacks details on return format, error behavior (e.g., max_runs cap), or what the CSV contains. Adequate but has gaps.

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 parameters are well-documented. The description adds high-level context about sweeping and output metric, but does not elaborate on parameter details beyond what schema provides. Baseline score appropriate.

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 uses specific verb 'sweep' and resource 'parameters', clearly stating it performs one-at-a-time sensitivity analysis and returns range slope and elasticity. It distinguishes itself from sibling tools like 'simulate' or 'validate_model'.

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 parameter influence analysis but does not explicitly state when to use this tool vs alternatives. It mentions a required dependency, which is helpful, but lacks when-not-to-use guidance.

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