Manufacturing management toolkit: TBP, quality, TPM, J-cost, OEE, vitality diagnostics.
Scored across 7 tools
Tools target distinct manufacturing domains (cost, equipment, quality, problem-solving, organization, analytics) and are distinguishable by their stated function. However, manufacturing_analytics overlaps with cost/device/quality tools because it analyzes similar data, creating some selection ambiguity about whether to use analytics or the domain-specific generator.
All names use snake_case and are descriptive; most follow a domain_noun pattern (cost_improvement, device_management, quality_management). Minor inconsistency: list_services uses verb_noun and tbp_problem_solving embeds an acronym, but the set remains readable and predictable.
Seven tools is well-scoped for a manufacturing management toolkit, with each module covering a distinct domain. No tool feels redundant or excessive.
The toolkit covers major consulting modules (cost, TPM, quality, TBP, org vitality, analytics) and includes a service catalog for discovery. Some adjacent domains (e.g., production planning, inventory management as standalone systems) are absent, but the surface is coherent for its stated purpose.
制造业成本改善与 J 成本论测算：由累计产量/累计成本数据算 J 成本、J 收益率，给出改善方向与敏感性分析。
Args:
points: 累计点数据 JSON 字符串，至少 2 个点，格式 [[累计产量, 累计成本], ...]，
例如 '[[0,0],[5,12000],[40,20000]]'。
profit: 单位利润（数字，可留空，例如 '8000'）。
payment_proof: 支付宝支付凭证。首次调用留空 → 返回付款信息；付款后带入此参数重试。
license_key: 买断/年费客户的授权码（有授权码则免付款）。与 payment_proof 填其一。
| Name | Required | Description | Default |
|---|---|---|---|
| points | Yes | ||
| profit | No | ||
| license_key | No | ||
| payment_proof | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and discloses key traits: a monetization gate with a two-step payment retry pattern, an authorization-code bypass, and a minimum of 2 data points. It stops short of describing error handling for malformed points or any rate/state behavior, so it is strong but not complete.
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 core purpose is front-loaded in one sentence, followed by a structured Args block that maps cleanly to the four parameters. It is appropriately sized for a computational tool with a payment gate, though the payment instructions are slightly verbose.
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?
An output schema exists, so return values need not be explained, and the description covers inputs, the minimum-points constraint, and the payment/authorization flow. It is nearly complete for this complexity, missing only failure/error behavior and confirmation of units or output determinism.
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 0%, so the description must compensate and largely does: it defines the points JSON string format with a concrete example, explains profit, and details the payment_proof/license_key alternatives and their relationship. Minor gap: profit is described as a number yet the schema types it (and the example) as a string, and units are not stated.
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 states a specific verb and resource: it computes J-cost and J-return rate from cumulative production/cost points and returns improvement directions plus sensitivity analysis. This is clearly distinct from siblings like device_management, quality_management, or manufacturing_analytics, so an agent can identify the tool without opening the schema.
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 gives a working flow for the payment gate (first call empty returns payment info, then retry with proof, or use a license_key), which is genuine when-to-use guidance. However, it says nothing about when to prefer this tool over manufacturing_analytics or other cost-related siblings, so usage relative to alternatives is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
设备管理全生命周期（TPM）系统：按设备清单生成保全方式选择、七维计划、点检标准、MTBF/OEE 指标与术语字典。
Args:
devices: 设备清单 JSON 字符串，至少 1 台，每台须有 id 与 name。
例如 '[{"id":"EQ-01","name":"注塑机","model":"HT-160"}]'。
payment_proof: 支付宝支付凭证。首次调用留空 → 返回付款信息；付款后带入此参数重试。
license_key: 买断/年费客户的授权码（有授权码则免付款）。与 payment_proof 填其一。
| Name | Required | Description | Default |
|---|---|---|---|
| devices | Yes | ||
| license_key | No | ||
| payment_proof | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does disclose the critical, non-obvious trait: the first call returns payment information rather than results, and the tool is gated behind Alipay payment or a license key. That is exactly the kind of context an agent needs. It stops short of 5 because it says nothing about rate limits, failure modes, or what the payment-gated response looks like structurally.
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 purpose sentence is front-loaded and the args are cleanly structured per parameter with no repetition. It is appropriately sized for a three-parameter tool with a payment flow, though the example is slightly verbose.
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?
An output schema exists, so return values need not be explained, and the definition covers the essential preconditions (required device format, payment/license gating). Nothing critical for a correct call is missing, though failure-handling and post-payment response expectations are not addressed.
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 0%, so the description must compensate, and it does: it defines devices as a JSON string with at least one entry requiring id and name, supplies a concrete example, and explains the payment_proof/license_key exclusivity. Only minor gaps remain (e.g. the full set of allowed device fields beyond id/name/model).
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 states a specific verb and resource: given a device list, it generates maintenance-method selection, a seven-dimension plan, inspection standards, MTBF/OEE indicators and a terminology dictionary. That is far more informative than the vague tool name 'device_management'. It does not compare itself to the siblings (quality_management, manufacturing_analytics, etc.), so it lands at 4 rather than 5.
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 gives clear invocation guidance for the payment gate: call first with payment_proof empty to receive payment info, then retry with the proof after paying, or supply a license_key to bypass payment entirely. It does not explain when to choose this tool over the sibling analysis tools, so it stops short of 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
列出本工具箱全部服务、价格与所需输入（下单前先看这个，或用于向用户报价）。
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It discloses what the call returns (services, prices, required inputs), which is useful, but never explicitly states that this is a read-only, side-effect-free operation, nor mentions permissions, caching, or rate limits. For a zero-parameter catalogue call the risk is low, hence a mid score rather than a penalty.
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?
A single sentence with the core purpose front-loaded and the usage hint placed in a trailing parenthesis. Nothing is padded, though the parenthetical is slightly informal and could be tightened.
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?
An output schema exists, so the description need not enumerate return fields, and with zero parameters the input side is trivially complete. The description covers what an agent needs in order to call it; only the explicit read-only guarantee 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?
The tool takes zero parameters, so there is nothing for the description to disambiguate. The baseline for a parameterless tool is 4, and the description correctly implies no input is needed.
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 gives a specific verb and resource: it lists all services in this toolbox along with prices and required inputs. That is far more informative than a tautology. It does not explicitly differentiate itself from the sibling tools, but those siblings (cost_improvement, device_management, etc.) are clearly unrelated domains, so confusion is unlikely.
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 usage context directly: consult it before ordering or when quoting prices to a user. That gives the agent a clear trigger. It stops short of naming exclusions or explicit alternatives, so it is clear context without full when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
制造业深度数据分析：对 OEE / SPC / 设备 / 库存 / 交期 / 成本 数据做多维度分析，输出结论与改善优先级。至少提供其中一项。
Args:
oee: OEE 相关数据（JSON 字符串）。
spc: 过程能力（Cpk 等）数据（JSON 字符串）。
device: 设备故障/停机数据（JSON 字符串）。
inventory: 库存数据（JSON 字符串）。
delivery: 交期/OTIF 数据（JSON 字符串）。
cost: 成本数据（JSON 字符串）。
payment_proof: 支付宝支付凭证。首次调用留空 → 返回付款信息；付款后带入此参数重试。
license_key: 买断/年费客户的授权码（有授权码则免付款）。与 payment_proof 填其一。
| Name | Required | Description | Default |
|---|---|---|---|
| oee | No | ||
| spc | No | ||
| cost | No | ||
| device | No | ||
| delivery | No | ||
| inventory | No | ||
| license_key | No | ||
| payment_proof | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does disclose an important non-obvious behavior: the payment/licensing workflow (first call with empty payment_proof returns payment info, then retry with proof, or use license_key). However it omits other traits an agent needs, such as whether the operation is read-only, whether submitted data is stored, and any rate or size limits.
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 purpose is front-loaded, then parameters are enumerated in a compact Args list. Every line maps to a parameter or the core behavior; there is no filler, though the two payment parameters are explained more verbosely than the six data parameters.
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?
An output schema exists, so return-format explanation is not owed, and the payment flow is covered. Still, for an eight-parameter analysis tool with zero annotation coverage, the description leaves gaps: the JSON shape expected for each data block and the read/compute semantics of the call are unstated, which an agent would need in order to invoke it correctly.
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 0%, so the description must compensate and largely does: all eight parameters are glossed, and the two workflow-critical ones (payment_proof, license_key) are explained in detail, including the first-call/retry flow and the 'fill one of the two' relationship. The gap is that the six data parameters are only labeled as JSON strings without any indication of expected structure.
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?
States a specific verb and resource: multi-dimensional analysis over six named manufacturing data domains (OEE/SPC/device/inventory/delivery/cost) producing conclusions and improvement priorities. It is clear what the tool does, though it never contrasts itself with plausible siblings such as cost_improvement, device_management, or quality_management that overlap with its input domains.
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 only usage rule given is '至少提供其中一项' (supply at least one of the data blocks), which is a prerequisite rather than routing guidance. It never says when to prefer this tool over the sibling analytics tools or when it is the wrong choice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
品质管理全生命周期系统：按丰田源头品质方法生成企划→研发→生产准备→号试→量产六阶段全套品质文档（QFD、DFMEA、控制计划等）。
Args:
company: 企业名称。
product_type: 产品类别，例如「注塑件」「电机」。
module: 只生成某一模块时填 Q1–Q10，全部生成填 ALL（默认）。
payment_proof: 支付宝支付凭证。首次调用留空 → 返回付款信息；付款后带入此参数重试。
license_key: 买断/年费客户的授权码（有授权码则免付款）。与 payment_proof 填其一。
| Name | Required | Description | Default |
|---|---|---|---|
| module | No | ALL | |
| company | No | ||
| license_key | No | ||
| product_type | No | ||
| payment_proof | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose the key behavioral trait: a two-step payment gate where the first call returns payment information, plus an alternative authorization path via license_key. It does not cover idempotency, generation duration, or whether existing documents are overwritten.
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 purpose sentence is front-loaded, and the arg-by-arg notes are compact and each earns its place by documenting otherwise-undocumented parameters. The Python-docstring formatting is slightly unusual for a tool description but not wasteful.
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?
An output schema exists, so return-value explanation is not required. Combined with the payment/authorization flow and per-parameter notes, an agent has enough to invoke correctly; the main residual gap is that the specific Q1–Q10 module semantics remain undefined.
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 0%, so the description must compensate and largely does: each of the 5 parameters is given meaning, including the module enum-like guidance (Q1–Q10 or ALL) that the schema itself lacks (0 enums). It does not enumerate the Q1–Q10 codes individually.
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 states a specific verb (generate) and resource (a full six-phase quality document set), naming concrete artifacts (QFD, DFMEA, control plan). It is clearly distinct in domain from siblings like cost_improvement or tbp_problem_solving, though it never explicitly contrasts itself with them.
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 gives concrete conditional usage: leave payment_proof empty on first call to receive payment info, then retry with the proof, or supply a license_key as an alternative ("填其一"). The module parameter usage (Q1–Q10 vs ALL) is also explained. No sibling-tool routing guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TBP 问题解决教练：用丰田 8 步法 + 5Why 三层 + 8×4 管理矩阵分析一个管理/设备/品质问题，输出完整分析报告。
Args:
problem: 问题描述。建议 15 字以上，写清「对象 + 现象 + 量化数据」，
例如「3 号注塑机频繁停机，每次 40 分钟」。
data: 问题相关的量化数据，例如「月停机 6 次共 4 小时」。
target: 改善目标，例如「月停机 ≤ 1 次」。
payment_proof: 支付宝支付凭证。首次调用留空 → 返回付款信息；付款后带入此参数重试。
license_key: 买断/年费客户的授权码（有授权码则免付款）。与 payment_proof 填其一。
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | ||
| target | No | ||
| problem | Yes | ||
| license_key | No | ||
| payment_proof | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden, and it does disclose the key non-obvious behavior: a first call without payment_proof returns payment information, and the call must be retried with proof, or a license_key can bypass it. This is genuinely important auth/payment context. It omits other traits such as whether the analysis is deterministic or how long the report is, keeping it out of 5 territory.
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?
Purpose is front-loaded in the first sentence, followed by a clean per-argument breakdown using the standard Args convention. Every section earns its place, though the payment paragraph repeats the license/payment relationship slightly.
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?
An output schema exists, so return values need not be described, and the description covers the invocation flow, parameter semantics, and the payment gate. The main gap is the absence of trigger conditions relative to sibling tools, which is the only missing piece for calling it correctly.
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 0%, so the description must compensate, and it does: each of the five parameters is explained with meaning plus a concrete example (e.g. the '3号注塑机' problem sample, quantified data, target threshold). It also clarifies that payment_proof and license_key are alternatives, resolving the mutual-exclusivity that the bare schema cannot express.
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 a specific verb+resource: analyzes a management/equipment/quality problem using named methodologies (Toyota 8-step, 5Why three layers, 8×4 matrix) and emits a full analysis report. That is concrete and actionable. It stops short of explicitly distinguishing itself from siblings such as quality_management or device_management, so it is clear but not fully differentiated.
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?
There is no guidance on when to choose this tool over the sibling tools (quality_management, device_management, cost_improvement), which are the obvious overlaps for a TBP analysis. The payment instructions describe an invocation flow but not selection criteria, so usage must be inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
活力组织诊断与建设方案：诊断组织活力、输出信任/希望/价值/挑战四维建设方案与落地清单。
Args:
industry: 所属行业。
headcount: 员工人数。
pain: 当前最困扰的组织问题。
goal: 期望达成的目标。
trust/hope/value/challenge: 四维评分 0–5（可留空，未填按行业基准估算）。
payment_proof: 支付宝支付凭证。首次调用留空 → 返回付款信息；付款后带入此参数重试。
license_key: 买断/年费客户的授权码（有授权码则免付款）。与 payment_proof 填其一。
| Name | Required | Description | Default |
|---|---|---|---|
| goal | No | ||
| hope | No | ||
| pain | No | ||
| trust | No | ||
| value | No | ||
| industry | No | ||
| challenge | No | ||
| headcount | No | ||
| license_key | No | ||
| payment_proof | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses that blank trust/hope/value/challenge scores are estimated from industry benchmarks, and it explains the two-phase paid-access model including the license_key alternative. It omits any statement about rate limits, data retention, or what happens on invalid credentials, so it is strong but not exhaustive.
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 purpose sentence is front-loaded and the argument list is dense and scannable, with no filler prose. The Args block is somewhat list-like, but each line delivers distinct parameter information rather than restating the schema.
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?
Because an output schema exists, the description need not narrate return values, and it focuses correctly on inputs and the access/payment flow. All ten inputs are covered and the two-call pattern is explained, though the agent receives no hint about prerequisite data quality or expected response shape beyond the schema.
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 0% (properties carry only titles and empty-string defaults), so the description must compensate and does: it explains every one of the ten parameters, including the 0–5 scale and optionality of the four dimension scores, the benchmark fallback, and the exact roles of payment_proof and license_key. This is materially more meaning than the bare schema provides.
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 a specific verb and resource: diagnosing organizational vitality and producing a four-dimension (trust/hope/value/challenge) construction plan with an implementation checklist. This is far more informative than a tautology, and the concrete deliverables make the tool's output identifiable. It does not, however, distinguish itself from siblings like tbp_problem_solving or cost_improvement, leaving an agent to infer the boundary.
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 gives clear operational context for the payment-gated flow: a first call with payment_proof empty returns payment information, and the caller retries with proof after paying, or supplies license_key to bypass payment. This is genuine when/how guidance for actually invoking the tool. It offers no guidance, though, on when this diagnosis is preferable to the sibling problem-solving or quality tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
cost_improvementdevice_managementlist_servicesmanufacturing_analyticsquality_managementtbp_problem_solvingvital_organizationManufacturing should-cost from CAD and drawings: cost drivers, process plan, lot sizes.
5,400+ manufacturing calculators plus live U.S. tariff, PMI, cost-index, wage, and forecast data.
Industrial glossary, protocol reference, technical search and OEE calculation. Read-only.
8-dimension business diagnosis with Revenue Leak Score and triple-option recommendations
Add one secure layer between your agents and this server.
