Run the Monte Carlo should-cost calculation on a cost model. Returns P50 (median), P80 and P90 cost-at-risk per unit, plus a full cost breakdown (material, labour, machine, overhead, margin).
| Name | Required | Description | Default |
|---|---|---|---|
| modelId | Yes | Cost model ID returned by create_cost_model. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided. The description implies a read-only calculation by saying 'Run' and 'Returns', but does not explicitly state side effects (e.g., whether it mutates the model) or any prerequisites like the model having materials/processes. It discloses outputs but not error conditions or permissions.
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 a single sentence, immediately states the action and the returns, and avoids any redundant or filler content. Every word adds value.
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 single-parameter tool with a clear schema and no output schema, the description sufficiently explains the purpose and return values. It lacks only mention of potential errors or prerequisites (e.g., that the model must exist), but this is largely covered by the schema field description. No major gaps remain.
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 description coverage is 100% (modelId documented as 'Cost model ID returned by create_cost_model'), so a baseline of 3 is appropriate. The tool description adds no additional meaning about the parameter beyond what the schema already states.
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 a specific verb-resource pair ('Run the Monte Carlo should-cost calculation on a cost model') and explicitly lists the outputs (P50, P80, P90, and cost breakdown). It clearly differentiates from siblings like estimate_part by focusing on a cost model rather than a part estimate.
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 the model must already exist via 'on a cost model' and the schema notes the ID comes from create_cost_model, but it does not state when to prefer this over alternatives like estimate_part, nor mention any exclusions (e.g., when a cost model is not ready). No explicit guidance for tool selection is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target a distinct action and resource: search vs. add vs. calculate vs. compare vs. review. The only mild ambiguity is between estimate_part and calculate_cost_model, but their descriptions clearly distinguish a quick natural-language estimate from running a full saved model.
All tool names follow a consistent verb_noun pattern using imperative verbs like create, add, calculate, compare, search, get, and review. This makes the tool surface predictable and easy to navigate.
Ten tools is well-scoped for a should-cost analysis domain. Each tool covers a clear stage in the workflow: model creation, component/process lookup, cost calculation, country comparison, and quote review.
The core should-cost workflow is covered well: create a model, add materials and processes, calculate, compare locations, benchmark quotes, and perform quick estimates. Minor gaps exist around updating or removing model contents and around broader lifecycle management, but agents can work around these.
