Estimate costs for a multi-part bill of materials in one call.
Each part: {process, quantity, material?, bounding_box_mm?, tolerance_mm?,
finish?}. Returns per-line estimates, a BOM total, and the longest lead
time. Indicative and non-binding. Max 50 lines.
| Name | Required | Description | Default |
|---|---|---|---|
| parts | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral disclosure burden. It states what the tool returns (per-line estimates, BOM total, longest lead time), the max 50-line limit, and the non-binding nature of results. It does not mention side effects, but as a cost estimation tool, the key behavioral aspects are covered.
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, front-loaded with the primary purpose, then detailing part structure and outputs. Every sentence earns its place without redundancy.
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 a single-parameter schema and no output schema, the description compresses the essential contract: purpose, field structure, return summary, and constraints. It omits details like allowed process values or quantity units, but the estimation context makes these less critical for correct invocation.
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 schema defines `parts` only as an array of objects with additionalProperties true, so the description is the sole source of field meaning. It lists expected fields (process, quantity, material?, bounding_box_mm?, tolerance_mm?, finish?) and marks optionality, adding significant value beyond the sparse schema.
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's purpose: 'Estimate costs for a multi-part bill of materials in one call,' specifying the verb (estimate), resource (multi-part bill of materials), and batch scope. This distinguishes it from siblings like get_lead_time or request_quote by emphasizing multi-part cost estimation.
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 context through 'Indicative and non-binding' and 'in one call,' suggesting this is for preliminary estimates rather than final quotes. However, it does not explicitly name alternatives or state when not to use the tool, so clear exclusions are missing.
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.
Each tool addresses a distinct aspect: discovery, single-part quotes, BOM estimation, process comparison, lead time, quote refinement, and DFM feedback. The slight overlap between request_quote and compare_processes is mitigated by their different purposes (single process vs. multi-process comparison).
Most tools follow a verb_noun pattern (compare_processes, request_quote, estimate_bom). dfm_feedback deviates because 'dfm' is not a verb, making it a minor inconsistency, but the overall naming remains readable and predictable.
Seven tools is well-scoped for a manufacturing estimation service. Each tool serves a distinct need with no redundancy, and the count is neither too sparse nor overwhelming for the domain.
The core workflow (discover capabilities, request quote, refine quote) is covered, along with BOM estimation and process comparison. However, there is no direct 'get_quote' tool to retrieve a previous estimate without refining it, which is a minor gap that can be worked around via refine_quote.