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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses that computations are pure arithmetic with no I/O or external calls, that results are rounded to 2 decimals, that foreign-method parameters are silently accepted and ignored, and that unknown methods or missing required parameters return an error rather than a value. It also carries the 1000-100000 iterations constraint on monte_carlo_sensitivity.

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 the purpose and routing rule before the per-method parameter inventory, and every sentence carries operational content. The middle section is a dense list, but the information density justifies the length.

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?

For a complex 11-parameter multi-method tool, the description covers routing, per-method parameter requirements, error behavior, and computational side-effects, and an output schema exists so return payloads need not be re-explained. Nothing an agent needs to invoke it correctly is missing.

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 the baseline is 3, but the description adds real value the flat schema lacks: a per-method required/optional breakdown (monte_carlo needs input_distributions; decision_tree needs tree; sensitivity_analysis needs function_name + parameter_name + parameter_range + fixed_parameters) and the rule that only method is required while others are method-dependent. It stops short of documenting the base_params/distributions shapes beyond what the schema already gives.

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 names the concrete capability set (Monte Carlo valuation, sensitivity ranking, decision-tree expected values, one-at-a-time sensitivity) with a clear verb+resource framing, and the method enum maps each formula to a distinct operation. It also names the sibling class it is not ('the relevant valuation tool') for point values, so an agent can separate it from the thirteen valuation_* siblings.

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?

It states when to use the tool ('quantify and stress the uncertainty around a point valuation'), when not (single deterministic point value -> relevant valuation tool), and how sensitivity_analysis differs from the core functions it wraps. Routing conditions are explicit rather than inferred.

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