tw-market-data

Screen the market

screen

Read-onlyIdempotent

Post-process rows already returned by query_dataset; without rows it returns a clear hint.

Turn a spoken shortlist description into explicit numeric cut-offs, and show the cut-offs.

★ THE THRESHOLDS COME BACK WITH THE SHORTLIST. "低本益比" becomes `per < 15`, and that 15 is
printed in `applied[]` so you can disagree with it. A filter that hands over thirty names
without saying where it drew the line cannot be checked by anyone — and whether the line was
15 or 20 completely changes which thirty.

★ PHRASES IT CANNOT MAP COME BACK IN `unparsed[]`. It will not quietly invent a boundary for
a wording it did not recognise, because a list the caller believes they defined and actually
did not is worse than a shorter list.

★ NOT `query_dataset` AND NOT `compare`. `query_dataset` returns rows for symbols you already
chose; `compare` puts a handful of named symbols beside each other. This one is for when you
have no symbols yet, only a description of what you are looking for.

⚠️ A shortlist is not a recommendation. Rows whose value is absent are excluded rather than
assumed to pass — being unmeasured is not the same as qualifying.
Args: conditions (plain words), optional as_of, optional pre-fetched rows.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`rows`	No
`as_of`	No
`conditions`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`note`	No
`as_of`	No
`applied`	No
`results`	No
`unparsed`	No
`rows_examined`	No
`not_investment_advice`	No
`thresholds_are_choices`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedAug 28, 2026

addedOutput schema / description

Added value: +"`screen` 的回傳。**逐欄對照實際 payload 寫的,不是照工具名猜的。**\n\n⚠️ `thresholds_are_choices` 不是雜訊欄,是這個工具的誠實邊界:\n篩選門檻是**我方選的**,不是市場給的。它要進 schema,否則 client 拿到\nstructuredContent 之後會把門檻當成客觀事實。\n\n⚠️ `extra=\"allow\"` 在這裡是必要的,不是保險:payload 尾端有\n`payload.update(input_guard_report(guarded))`,那些鍵是動態的。\n宣告成 forbid 會讓每一次帶 guard 報告的回應驗證失敗 —— 而 FastMCP\n驗不過時整個 structuredContent 會被丟掉,client 收到的是空的。"

addedOutput schema / properties

Added value: +{
+  "applied": {
+    "anyOf": [
+      {
+        "items": {},
+        "type": "array"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Applied"
+  },
+  "as_of": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "As Of"
+  },
+  "not_investment_advice": {
+    "anyOf": [
+      {
+        "type": "boolean"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Not Investment Advice"
+  },
+  "note": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Note"
+  },
+  "results": {
+    "anyOf": [
+      {
+        "items": {},
+        "type": "array"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Results"
+  },
+  "rows_examined": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Rows Examined"
+  },
+  "thresholds_are_choices": {
+    "anyOf": [
+      {},
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Thresholds Are Choices"
+  },
+  "unparsed": {
+    "anyOf": [
+      {
+        "items": {},
+        "type": "array"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Unparsed"
+  }
+}

changedOutput schema / title

Previous value: -"screenDictOutput"New value: +"ScreenResult"

AddedAug 24, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Adds substantial behavior beyond annotations: thresholds are echoed in applied[], unmappable phrases are surfaced in unparsed[] rather than invented, rows with absent values are excluded rather than assumed to pass, and the no-rows case returns a hint. Annotations (readOnly/idempotent/openWorld) only cover the safety profile, so this disclosure is genuinely additive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose in the first sentence, and each starred block carries a distinct guarantee (thresholds echoed, unparsed phrases preserved, sibling disambiguation, null handling). The heavy ★/⚠️ decoration and 'shortlist is not a recommendation' framing add length without much extra selection value, but no sentence is truly redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a natural-language screening tool with an output schema present, the description supplies everything an agent needs: the input contract (conditions/as_of/rows), the output semantics (applied[], unparsed[]), null-value handling, and sibling routing. Return-value formatting is correctly left to the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the load, and it does name all three args: conditions as plain words, optional as_of, optional pre-fetched rows. It also clarifies the rows parameter's behavior when omitted ('returns a clear hint'), though it gives no format guidance for as_of or the row shape.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: turning a spoken shortlist description into explicit numeric cut-offs over rows, and producing a shortlist with applied thresholds. It also explicitly names what it is not (query_dataset, compare), so an agent can distinguish it from siblings without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use: 'for when you have no symbols yet, only a description of what you are looking for.' It excludes query_dataset ('returns rows for symbols you already chose') and compare ('puts a handful of named symbols beside each other'), and states the precondition that pre-fetched rows feed it in.

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

All tw-market-data tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?