Skip to main content
Glama
24mlight

A-Share MCP Server

get_forecast_report

Generate earnings forecast reports for A-share stocks within specified date ranges to analyze company performance projections.

Instructions

Earnings forecast report within date range.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeYes
start_dateYes
end_dateYes
limitNo
formatNomarkdown

Implementation Reference

  • The main MCP tool handler for 'get_forecast_report', decorated with @app.tool(). It invokes the fetch_forecast_report helper via run_tool_with_handling.
    @app.tool()
    def get_forecast_report(code: str, start_date: str, end_date: str, limit: int = 250, format: str = "markdown") -> str:
        """Earnings forecast report within date range."""
        return run_tool_with_handling(
            lambda: fetch_forecast_report(
                active_data_source, code=code, start_date=start_date, end_date=end_date, limit=limit, format=format
            ),
            context=f"get_forecast_report:{code}:{start_date}-{end_date}",
        )
  • Helper function that calls data_source.get_forecast_report(), formats the DataFrame output using format_table_output, and handles validation.
    def fetch_forecast_report(data_source: FinancialDataSource, *, code: str, start_date: str, end_date: str, limit: int, format: str) -> str:
        validate_output_format(format)
        df = data_source.get_forecast_report(code=code, start_date=start_date, end_date=end_date)
        meta = {"code": code, "start_date": start_date, "end_date": end_date, "dataset": "Forecast"}
        return format_table_output(df, format=format, max_rows=limit, meta=meta)
  • Concrete implementation of get_forecast_report in BaostockDataSource, using bs.query_forecast_report to fetch data from Baostock API, with full error handling and pagination support.
    def get_forecast_report(self, code: str, start_date: str, end_date: str) -> pd.DataFrame:
        """Fetches performance forecast reports (业绩预告) using Baostock."""
        logger.info(
            f"Fetching Performance Forecast Report for {code} ({start_date} to {end_date})")
        try:
            with baostock_login_context():
                rs = bs.query_forecast_report(
                    code=code, start_date=start_date, end_date=end_date)
                # Note: Baostock docs mention pagination for this, but the Python API doesn't seem to expose it directly.
                # We fetch all available pages in the loop below.
    
                if rs.error_code != '0':
                    logger.error(
                        f"Baostock API error (Forecast) for {code}: {rs.error_msg} (code: {rs.error_code})")
                    if "no record found" in rs.error_msg.lower() or rs.error_code == '10002':
                        raise NoDataFoundError(
                            f"No performance forecast report found for {code} in range {start_date}-{end_date}. Baostock msg: {rs.error_msg}")
                    else:
                        raise DataSourceError(
                            f"Baostock API error fetching performance forecast report: {rs.error_msg} (code: {rs.error_code})")
    
                data_list = []
                while rs.next():  # Loop should handle pagination implicitly if rs manages it
                    data_list.append(rs.get_row_data())
    
                if not data_list:
                    logger.warning(
                        f"No performance forecast report found for {code} in range {start_date}-{end_date} (empty result set).")
                    raise NoDataFoundError(
                        f"No performance forecast report found for {code} in range {start_date}-{end_date} (empty result set).")
    
                result_df = pd.DataFrame(data_list, columns=rs.fields)
                logger.info(
                    f"Retrieved {len(result_df)} performance forecast report records for {code}.")
                return result_df
    
        except (LoginError, NoDataFoundError, DataSourceError, ValueError) as e:
            logger.warning(
                f"Caught known error fetching performance forecast report for {code}: {type(e).__name__}")
            raise e
        except Exception as e:
            logger.exception(
                f"Unexpected error fetching performance forecast report for {code}: {e}")
            raise DataSourceError(
                f"Unexpected error fetching performance forecast report for {code}: {e}")
Behavior2/5

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It mentions 'earnings forecast report' and 'date range' but doesn't specify what the report contains, whether it's paginated (limit parameter exists), authentication requirements, rate limits, or error conditions. For a tool with 5 parameters and no annotations, this is inadequate transparency.

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

Conciseness5/5

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

The description is a single, efficient sentence with no wasted words. It's appropriately sized for a simple tool and front-loads the key information (earnings forecast report, date range). Every word earns its place.

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

Completeness2/5

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

Given the complexity (5 parameters, 3 required), no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns, how to interpret parameters, or behavioral aspects. For a data retrieval tool with multiple parameters, more context is needed to make it usable by an AI agent.

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

Parameters2/5

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

Schema description coverage is 0%, so the schema provides only parameter names and types without descriptions. The description mentions 'date range' which hints at start_date and end_date, and 'earnings forecast report' hints at code (likely stock/company code). However, it doesn't explain the format parameter options, what limit controls, or provide any parameter details beyond basic hints. With 5 parameters and 0% schema coverage, the description doesn't adequately compensate.

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

Purpose3/5

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

The description states the tool retrieves an 'earnings forecast report within date range', which specifies the resource (earnings forecast report) and scope (date range). However, it doesn't clearly differentiate from siblings like get_profit_data or get_performance_express_report that might also provide financial performance data. The purpose is clear but lacks sibling differentiation.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives. With many sibling tools for financial data (e.g., get_profit_data, get_performance_express_report), the description doesn't indicate this is specifically for forecast/forward-looking earnings versus historical data or other report types. Usage is implied by the name but not explicitly stated.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/24mlight/a-share-mcp-is-just-i-need'

If you have feedback or need assistance with the MCP directory API, please join our Discord server