Skip to main content
Glama

agentladle/financial-reports

getFinancialReportPages

getFinancialReportPages
Destructive

Read full page content from a financial report by page range.

<critical_rules>

  1. startPage is 1-based. pageCount defaults to 5, max 5.

  2. Report types by market (approx. last 3 years; pick {year} from the user request, do not invent older years):

    • CN-A: annual '{year}a4', interim '{year}h2', Q1 '{year}q1', Q3 '{year}q3'.

    • HK: annual '{year}a4', interim '{year}h2' only (no quarterly).

  3. Stock code format: CN-A 6 digits (000001), HK 5 digits (00700). Prefer stockCode and market returned by searchCompanyInfo. Do not invent padding.

  4. market is optional ('CN-A' | 'HK'). Omit to search all markets.

  5. For specific facts, prefer financialKeywordSearch first — it is faster than reading pages sequentially. </critical_rules>

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "stockCode": "<stockCode>",
      "reportType": "<reportType>",
      "startPage": "<startPage>"
    },
    "name": "getFinancialReportPages"
  }
}

Input Schema

NameRequiredDescriptionDefault
marketNoMarket: 'CN-A' | 'HK'. Optional. Omit to search all markets.
pageCountNoNumber of pages to return, default 5, max 5
startPageYesStart page (1-based)
stockCodeYesStock code from searchCompanyInfo. CN-A: 6 digits; HK: 5 digits.
reportTypeYesReport type. CN-A: {year}a4|{year}h2|{year}q1|{year}q3; HK: {year}a4|{year}h2

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / reportType / description
      Previous value: -"Report type, e.g. 2025a4 (annual), 2026h2 (interim)"New value: +"Report type. CN-A: {year}a4|{year}h2|{year}q1|{year}q3; HK: {year}a4|{year}h2"
  2. Changed2 schema fields changed
    • changedInput schema / properties / market / description
      Previous value: -"Market: 'CN-A' | 'HK' | 'US'. Optional. Omit to search all markets."New value: +"Market: 'CN-A' | 'HK'. Optional. Omit to search all markets."
    • changedInput schema / properties / stockCode / description
      Previous value: -"Stock code from searchCompanyInfo. CN-A: 6 digits; HK: 5 digits; US: uppercase ticker."New value: +"Stock code from searchCompanyInfo. CN-A: 6 digits; HK: 5 digits."
  3. Changed5 schema fields changed
    • addedInput schema / properties / market
      Added value: +{
      +  "description": "Market: 'CN-A' | 'HK' | 'US'. Optional. Omit to search all markets.",
      +  "type": "string"
      +}
    • changedInput schema / properties / pageCount / description
      Previous value: -"返回页数(最多5页)"New value: +"Number of pages to return, default 5, max 5"
    • changedInput schema / properties / reportType / description
      Previous value: -"报告类型标识符(当前已支持如:2023a4,2024a4,2025a4)"New value: +"Report type, e.g. 2025a4 (annual), 2026h2 (interim)"
    • changedInput schema / properties / startPage / description
      Previous value: -"起始页码"New value: +"Start page (1-based)"
    • changedInput schema / properties / stockCode / description
      Previous value: -"股票代码"New value: +"Stock code from searchCompanyInfo. CN-A: 6 digits; HK: 5 digits; US: uppercase ticker."
  4. First observed

TDQS

A3.9/5.0
Behavior1/5

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

The description frames the tool purely as a read operation ('Read full page content', 'READ BY KNOWN PAGE', 'it is faster than reading pages'), but the annotations declare readOnlyHint=false and destructiveHint=true. An agent trusting the prose would treat this as a safe retrieval call, while the annotations warn of a non-read-only, destructive side effect; the mismatch is never acknowledged or explained.

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?

The description is front-loaded with the one-line purpose, then organized into <strategy> and <critical_rules> blocks that are easy to scan. It loses a point for restating structured facts already in the schema (pageCount defaults/max, market optional, digit lengths), but the redundancy is small relative to the useful content.

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

Completeness4/5

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

For a five-parameter, no-output-schema retrieval tool, the description covers prerequisite chaining (searchCompanyInfo), valid report-type vocabularies per market, page-boundary conventions, and market coverage (CN-A and HK only). The main remaining gap is that it never says what a returned 'page' looks like — whether headers, tables, or page numbers are included — which matters when paging through a TOC.

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 coverage is 100%, so the baseline is 3, and the description goes beyond it by adding operating knowledge: pass back the stockCode + market pair from searchCompanyInfo, do not invent padding, pick {year} from the user request and avoid report types older than roughly three years, and use startPage values obtained from a TOC or keyword-search result. Most remaining details (pageCount max 5, market optional, digit formats) repeat what the schema already says.

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?

The opening sentence gives a specific verb, resource, and retrieval unit: 'Read full page content from a financial report by page range.' It also implicitly separates itself from keyword search by emphasizing 'full page content' and the page-range mechanism, so an agent can tell it apart from financialKeywordSearch without inspecting 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?

The <strategy> block gives explicit when-to-use branches: read by known page when startPage comes from financialKeywordSearch or a TOC, discover structure by starting at page 1 with pageCount 3-5, and call searchCompanyInfo first when the company is unknown. Rule 5 states the exclusion outright ('prefer financialKeywordSearch first — it is faster than reading pages sequentially'), which is exactly the routing guidance this dimension rewards.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources