Standardized DCF valuation engine for stocks (A-shares, Hong Kong, US, Japan). Two-phase analyst workflow via one run_dcf tool: baseline from 5-year historicals, then a final valuation with reasoned assumptions — value bridge, sensitivity matrix, reverse DCF. A-shares & HK need no API key.
Scored across 3 tools
Each tool addresses a distinct analytical question: relative historical valuation (get_relative_valuation), composite quality/growth/momentum score (get_score), and intrinsic DCF value (run_dcf). The descriptions explicitly cross-reference one another and clarify when to use each, leaving no meaningful ambiguity.
Two tools follow a clean get_<noun> pattern, while run_dcf breaks the pattern by using run_ to signal a multi-step computation workflow. Naming is still readable and consistently snake_case, with only a minor verb-style deviation.
Three tools form a tightly scoped valuation and analysis suite. Each tool earns its place—relative valuation, quick health score, and full DCF—without redundancy or padding, fitting well within the ideal 3-15 range.
The suite covers the core equity-analysis workflow: relative positioning, composite scoring, and intrinsic value. Minor gaps exist—such as no direct peer-comparable valuation tool—but the descriptions acknowledge this limitation and the overall surface feels complete for its stated purpose.
相对估值：当前倍数 + 自身历史分位。秒回，不需要任何假设参数。
回答"这只票相对自己的历史贵不贵"——与 run_dcf 互补而非替代：
run_dcf 算的是内在价值（这家公司值多少），本工具算的是相对位置
（市场现在给它的倍数处于历史什么水平）。两者应互相验证：若 DCF 显示
低估而倍数处于历史高位，必须解释这个矛盾。
返回：
- current —— 当前 P/E、Forward P/E、P/B、P/S、EV/EBITDA
- historical —— P/E 与 P/B 的历史区间和当前分位（百分位越低越便宜）
注意分位只与公司自身历史比较，不含可比公司横向对比；判断行业是否
整体重估时，仍需结合同业倍数。years 可取 1-10，默认 5 年。
ticker 格式同 run_dcf。A股/港股无需 key；美股/日股需要 FMP key 或
使用每日限量的免费体验额度。
| Name | Required | Description | Default |
|---|---|---|---|
| years | No | ||
| ticker | Yes | ||
| fmp_api_key | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses the fast '秒回' behavior, notes that no assumption parameters are needed, describes the exact output fields, states the historical percentile limitation, and specifies the years range and API key requirements for different markets. Since no annotations are provided, this description carries the full behavioral burden and does so thoroughly.
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 longer than minimal but well structured with a bolded headline, a clear complementary-vs-alternative explanation, bullet-like return sections, and concise usage notes. Every section earns its place, though a sentence or two could be trimmed without losing 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?
Given no output schema and no annotations, the description is remarkably complete: it lists the returned current and historical metrics, explains the percentile meaning, covers the cross-company comparison caveat, specifies the years range, and documents API key requirements by market. An agent has enough information to select the tool and 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. It explains that years can be 1–10 with a default of 5, indicates that ticker format follows run_dcf, and clarifies when fmp_api_key is needed (US/Japan) versus not needed (A-shares/HK). It could be slightly more explicit about the exact ticker format and the meaning of an empty fmp_api_key, but it provides substantial meaning beyond the raw 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 identifies the tool as computing relative valuation (current multiples plus the company's own historical percentile) and explicitly answers the question 'is this stock expensive relative to its own history'. It also distinguishes itself from run_dcf by contrasting intrinsic value with relative position, so an agent can tell them apart immediately.
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 explicitly says this tool is complementary to rather than a replacement for run_dcf, and explains when to prefer each: run_dcf for intrinsic value and this tool for historical positioning. It even instructs that the two should be cross-validated, and warns that industry-wide re-rating still requires comparable-company multiples.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
四维综合评分（估值/质量/成长/动量，各 25%）。秒回，不需要假设参数。
用于快速体检一家公司：每个维度 0-100 独立打分后等权合成总分。
- 估值 —— 相对自身历史是否便宜（PE 历史分位、Forward PE、经营 PE）
- 质量 —— 是否经营得好（ROE 水平与趋势、收入与利润率趋势、杠杆、
Piotroski F 分、利润质量）
- 成长 —— 是否在增长（预期 EPS 增速、3 年收入 CAGR、最新收入增速）
- 动量 —— 市场是否在奖励它（12-1 月、6-1 月收益，剔除最近 1 个月）
这是**相对指标的体检，不是内在价值判断**：估值维度用的是 PE 分位而非
DCF。要回答"值多少钱"请用 run_dcf；要回答"这公司整体怎么样"用本工具。
ticker 格式同 run_dcf。A股/港股无需 key；美股/日股需要 FMP key 或
使用每日限量的免费体验额度。
| Name | Required | Description | Default |
|---|---|---|---|
| ticker | Yes | ||
| fmp_api_key | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and does well: it discloses the scoring methodology, equal weighting, 0-100 per dimension, fast response ('秒回'), no assumption parameters, relative vs intrinsic scope, and API key requirements/rate limits. It stops short of describing the exact return shape or failure modes.
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 well-structured and front-loaded: a one-line summary of the composite score, a concise bullet list of dimensions with sub-metrics, then caveats and routing. Every sentence adds value, and the length is justified by the tool's methodology.
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?
The description is largely complete for a tool with no annotations and no output schema: it covers purpose, methodology, alternatives, key requirements, and ticker-format reference. The main gaps are the lack of explicit guidance about get_relative_valuation and no detail on the exact output structure, though the scoring description implies the return content.
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%, but the description compensates by adding conditional meaning: ticker format is said to match run_dcf, and fmp_api_key is conditionally required depending on market (A股/港股 no key, 美股/日股 key or limited free quota). This goes beyond the bare schema, though ticker format itself is delegated to a sibling rather than fully specified.
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 computes a four-dimensional composite score (估值/质量/成长/动量, equal 25% weights) as a quick company health check. It distinguishes itself from run_dcf by explicitly saying it is a relative-indicator check, not an intrinsic-value judgment, but it does not explicitly differentiate from the sibling get_relative_valuation.
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 explicit when-to-use guidance: use it for '这公司整体怎么样' and use run_dcf for '值多少钱', and it states the key prerequisites for different markets (A股/港股 no key; 美股/日股 need FMP key or free quota). However, it never mentions when to prefer get_relative_valuation instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
一站式 DCF 估值（10 年两阶段 FCFF 折现），分两步使用：
第一步——不带任何假设参数调用：返回分析材料，含历史财务数据、每个参数的历史
区间、引擎算出的 WACC 与历史平均税率，以及 parameter_analysis_guide（资深分析师
参数分析指南）。**此步不返回估值**——先给一个数字只会锚定你接下来的判断。收到后
请按指南对每个参数做独立分析（若有联网搜索能力，务必先按指南搜索业绩指引与
分析师预期），然后进入第二步。
第二步——带上你分析得出的假设参数再次调用：返回最终估值，含每股内在价值、
与市价差异、价值桥、逐年预测表、敏感性矩阵、反向 DCF（市价隐含假设）。
参数单位：增长率/利润率/税率/WACC 为百分数（10 表示 10%）；
revenue_invested_capital_ratio 为倍数（如 2.0）；convergence 为收敛年数。
省略 tax_rate/wacc 时由引擎按财报与市场数据自动计算。
include_history_chart=true 时额外返回一张历史趋势图（PNG，2×2：营收与增速、
EBIT 利润率、Rev/IC、再投资额）——用户想看关键假设的历史数据可视化时使用。
ticker 格式：A股 600519.SS / 000333.SZ；港股 0700.HK；美股 AAPL；日股 7203.T。
A股/港股无需 key。美股/日股需要 FMP key：可通过 fmp_api_key 参数传入，或在
MCP 连接配置中设置 X-FMP-Key 请求头；未提供时可使用每日限量的免费体验额度。
FMP 注册（valuescope 优惠码有折扣）：
https://site.financialmodelingprep.com/pricing-plans?couponCode=valuescope
| Name | Required | Description | Default |
|---|---|---|---|
| wacc | No | ||
| ticker | Yes | ||
| tax_rate | No | ||
| convergence | No | ||
| ebit_margin | No | ||
| fmp_api_key | No | ||
| revenue_growth_1 | No | ||
| revenue_growth_2 | No | ||
| ronic_match_wacc | No | ||
| include_history_chart | No | ||
| revenue_invested_capital_ratio_1 | No | ||
| revenue_invested_capital_ratio_2 | No | ||
| revenue_invested_capital_ratio_3 | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
没有任何 annotations，描述承担了行为透明度的全部责任。它主动披露了第一步骤'不返回估值'是为了避免锚定效应，第二步骤的返回值内容，以及省略 tax_rate/wacc 时自动计算、包括网络配额限制、美股日股 key 的传递方式等。这些披露远超单纯说明工具功能，Agent 能够准确预测每次调用的输出行为和边界条件。
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?
整体采用分步结构，先行为流程后参数格式，信息密度较高且层次清楚。但描述包含'FMP 注册（valuescope 优惠码有折扣）+ 推广 URL'一类对 AI Agent 调用无帮助的营销信息，且涉及'若有联网搜索能力，请先按指南搜索'这一类工作流程指导而非工具行为说明，增加了文本长度，略冗余。
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?
该工具具有 13 个参数、无输出 schema、无 annotations，且需描述两阶段调用、不同市场的密钥需求、参数单位与历史图表条件，描述覆盖了绝大多数关键信息。唯一明显缺口是 ronic_match_wacc 的语义没有说明，同时对营收增长两阶段与收敛年数之间的交互关系也未深度解释，整体上文较完整优。
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 描述覆盖率为 0%，描述大量补偿了参数含义：明确增长率/利润率/税率/WACC 为百分数、revenue_invested_capital_ratio 为倍数、convergence 为收敛年数，并给出了 ticker 格式。但 ronic_match_wacc 参数完全没有解释，revenue_growth_1 与 revenue_growth_2 在两个阶段中的分工也只是通过工具名称隐含，未完全明确。
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?
描述明确指明工具是'一站式 DCF 估值（10 年两阶段 FCFF 折现）'，并用两步操作流程进一步定义行为边界，属于具体动词+资源+方法的完整表达。即使没有 sibling 工具，Agent 也能准确理解该工具是用于生成 DCF 估值而非其他估值方式。
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?
描述明确规定了先不带参数调用（获取分析材料），再按分析结果带参数调用（得到估计值），并说明这两个步骤的顺序和目的。同时明确说明 include_history_chart=true 的适用场景、A股/港股无需 key 以及美股/日股需要 FMP key 的前提条件；这超出了默认所需的使用指引。
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.
get_relative_valuationget_scorerun_dcf
Add one secure layer between your agents and this server.