**IMPORTANT:** This endpoint requires structured queries using specific field names. 
    Simple natural language queries like "CDK2 gene" or "human kinase" will **NOT** work.
    You **MUST** specify the field you are querying, e.g., `symbol:CDK2`, `name:"cyclin-dependent kinase 2"`, `taxid:9606`.
    Use this tool when you need to *search* for genes based on criteria, not when you already know the specific gene ID.
    If you know the exact Entrez or Ensembl ID, use the `get_gene` tool instead for faster retrieval.
    
    **Supported Query Features (based on Lucene syntax):**
    1. Simple Term Queries: `q=cdk2` (Searches across default fields)
    2. Fielded Queries: `q=symbol:CDK2`, `q=name:"cyclin-dependent kinase 2"`
    3. Range Queries: `q=taxid:[9606 TO 10090]`
    4. Boolean Queries: `q=symbol:CDK2 AND taxid:9606`
    5. Wildcard Queries: `q=symbol:CDK*`
    
    Returns gene details including symbol, name, taxid, and entrezgene.
    

    Perform multiple gene searches in a single request using a comma-separated list of query terms.
    Unlike `query_genes`, the `query_list` parameter takes multiple **terms** (like gene IDs, symbols, names) 
    rather than full query strings. The `scopes` parameter defines which fields these terms should be searched against.
    
    **Endpoint Usage:**
    - Query multiple symbols: `query_list=CDK2,BRCA1` with `scopes=symbol`
    - Query multiple Entrez IDs: `query_list=1017,672` with `scopes=entrezgene`
    - Query mixed IDs/symbols: `query_list=CDK2,672` with `scopes=symbol,entrezgene`
    

    Retrieves detailed information for a **single, specific gene** using its exact known identifier.
    **This is the preferred tool over `query_genes` for fetching a specific gene when you already know 
    its standard ID (Entrez or Ensembl) and don't need complex search filters.**
    
    **Supported Identifiers:**
    - Entrez Gene ID: e.g., `1017`
    - Ensembl Gene ID: e.g., `ENSG00000123374`
    

    Retrieves detailed information for **multiple specific genes** in a single request using their exact known identifiers.
    **This is the preferred tool over `query_many_genes` for fetching multiple specific genes when you already know 
    their standard IDs (Entrez, Ensembl) and don't need complex search filters.**
    
    **Input Format:** Accepts a comma-separated list of gene IDs (Entrez or Ensembl).
    **Example:** `gene_ids=1017,1018` or `gene_ids=ENSG00000123374,ENSG00000134057`
    

    Retrieve metadata about the underlying MyGene.info gene annotation database, **NOT** information about specific genes.
    **Use this tool ONLY to understand the database itself** (e.g., to discover available fields, check data versions, 
    or get overall statistics). It **CANNOT** be used to find or retrieve data for any particular gene.
    
    **Returned Information:**
    - `stats`: Database statistics (e.g., total number of genes)
    - `fields`: Available gene annotation fields and their data types
    - `index`: Information about the backend data index
    - `version`: Data version information
    

    Search for variants using a query string with various filtering options, leveraging the MyVariant.info API.
    **Use this tool for *searching* variants based on criteria.** 
    If you already know the exact variant ID (HGVS, rsID), use the `get_variant` tool for faster direct retrieval.

    **Supported Query Features (Lucene syntax):**
    1. Simple Queries: `q=rs58991260` (Find by rsID)
    2. Fielded Queries: `q=dbsnp.vartype:snp`, `q=dbnsfp.polyphen2.hdiv.pred:(D P)`
    3. Range Queries: `q=dbnsfp.polyphen2.hdiv.score:>0.99`
    4. Wildcard Queries: `q=dbnsfp.genename:CDK*`
    5. Boolean Queries: `q=_exists_:dbsnp AND dbsnp.vartype:snp`
    6. Genomic Interval Queries: `q=chr1:69000-70000`
    

    Perform multiple variant queries in a single request using a comma-separated list of variant identifiers.
    This tool takes multiple **terms** (like rsIDs, HGVS IDs) in `query_list` and searches for them within the specified `scopes`.
    
    **Endpoint Usage:**
    - Query multiple rsIDs: `query_list=rs58991260,rs2500` with `scopes=dbsnp.rsid`
    - Query multiple HGVS IDs: `query_list=chr7:g.140453134T>C,chr1:g.69511A>G`
    - Query mixed IDs: `query_list=rs58991260,chr1:g.69511A>G` with `scopes=dbsnp.rsid,_id`
    

    Retrieves detailed annotation data for a **single, specific variant** using its identifier.
    **This is the preferred tool over `query_variants` for fetching a specific variant when you already know 
    its standard ID (HGVS or rsID) and don't need complex search filters.**
    
    **Supported Identifiers:**
    - HGVS ID (e.g., `chr7:g.140453134T>C`). *Note: MyVariant.info primarily uses hg19-based HGVS IDs.*
    - dbSNP rsID (e.g., `rs58991260`)
    

    Retrieves annotation data for **multiple specific variants** in a single request using their identifiers.
    **This is the preferred tool over `query_many_variants` for fetching multiple specific variants when you already know 
    their standard IDs (HGVS or rsID).**

    **Input Format:** Accepts a comma-separated list of variant IDs (HGVS or dbSNP rsIDs).
    **Examples:** `variant_ids=chr7:g.140453134T>C,chr1:g.69511A>G` or `variant_ids=rs58991260,rs2500`
    

    Search for chemical compounds using a query string with various filtering options.
    
    **Supported Query Features:**
    1. Simple Queries: "C6H12O6" - Find compounds with molecular formula, "glucose" - Find compounds with name
    2. Fielded Queries: "pubchem.molecular_formula:C6H12O6", "pubchem.molecular_weight:[100 TO 200]"
    3. Range Queries: "pubchem.xlogp:>2", "pubchem.topological_polar_surface_area:[50 TO 100]"
    4. Boolean Queries: "pubchem.hydrogen_bond_donor_count:>2 AND pubchem.hydrogen_bond_acceptor_count:>4"
    
    Returns compound details including PubChem data like formula, weight, and XLogP.
    

    Perform multiple chemical queries in a single request.
    
    **Supported Usage:**
    1. Multiple Query Types: ["C6H12O6", "C12H22O11"] (formulas), ["glucose", "sucrose"] (names)
    2. Field Scoping: Search in specific fields using scopes parameter
    3. Result Filtering: Return specific fields using fields parameter
    

    Retrieves detailed information about a specific chemical compound using its identifier.
    
    **Supported ID formats:**
    - InChIKey: "KTUFNOKKBVMGRW-UHFFFAOYSA-N" (Glucose)
    - PubChem CID: "5793" (Glucose)
    - SMILES: "C([C@@H]1[C@H]([C@@H]([C@H]([C@H](O1)O)O)O)O"
    
    Returns comprehensive chemical information including structural properties, physical properties, 
    chemical properties, stereochemistry information, and chemical identifiers.
    

    Retrieves information for multiple chemical compounds in a single request.
    
    **Input Format:** Accepts comma-separated list of chemical IDs in various formats:
    - InChIKeys: "KTUFNOKKBVMGRW-UHFFFAOYSA-N,XEFQLINVKFYRCS-UHFFFAOYSA-N"
    - PubChem CIDs: "5793,5281"
    - Mixed formats: "KTUFNOKKBVMGRW-UHFFFAOYSA-N,5281"
    

    Retrieves detailed information about a specific taxon using its identifier.
    
    **Supported Identifiers:**
    - NCBI ID: 9606 (Homo sapiens)
    - Scientific name: "Homo sapiens"
    
    Returns comprehensive taxon information including basic information (ID, scientific name, common name),
    taxonomic classification (rank, parent taxon), lineage information, alternative names and authorities,
    and gene data availability.
    

    Retrieves information for multiple taxa in a single request.
    
    **Input Format:** Accepts comma-separated list of taxon IDs (either NCBI IDs or scientific names).
    **Examples:**
    - Multiple NCBI IDs: "9606,10090" (Homo sapiens and Mus musculus)
    - Multiple scientific names: "Homo sapiens,Mus musculus"
    - Mixed IDs: "9606,Mus musculus" (Homo sapiens by NCBI ID and Mus musculus by name)
    

    Search for taxa using a query string with various filtering options.
    
    **Supported Query Features:**
    1. Simple Queries: "scientific_name:Homo sapiens", "common_name:human"
    2. Fielded Queries: "rank:species", "parent_taxid:9606", "has_gene:true"
    3. Range Queries: "taxid:[9606 TO 10090]", "lineage:>9606"
    4. Boolean Queries: "rank:species AND has_gene:true", "scientific_name:Homo* AND NOT rank:genus"
    5. Wildcard Queries: "scientific_name:Homo*", "common_name:*mouse*"
    

    Perform multiple taxon queries in a single request.
    
    **Supported Usage:**
    1. Multiple Query Types: ["Homo sapiens", "Mus musculus"] (scientific names), ["human", "mouse"] (common names)
    2. Field Scoping: Search in specific fields using scopes parameter: ["scientific_name", "common_name"]
    3. Result Filtering: Return specific fields using fields parameter: ["scientific_name", "common_name", "rank"]
    

        Downloads data records from specified NCBI Entrez databases. This tool is designed to be called 
        by automated agents (like LLMs) or other services.

        **Critical Configuration:**
        The server hosting this API *must* have the `ENTREZ_EMAIL` environment variable set
        to a valid email address. NCBI requires this for Entrez queries to monitor usage
        and prevent abuse. Without it, NCBI may block requests.

        **Parameters:**
        - `ids` (List[str], required): A list of unique identifiers for the records to fetch
          from the specified Entrez database. Example: `["NM_000546.6", "AY123456.1"]`
        - `db` (DB_LITERAL, required): The target NCBI Entrez database.
          Common choices for sequences: 'nucleotide', 'protein'.
          Other examples: 'gene', 'pubmed', 'taxonomy'.
          Ensure the `ids` provided are appropriate for the selected `db`.
        - `reftype` (Literal["fasta", "gb"], required): The desired format for the
          downloaded data.
            - "fasta": Returns data in FASTA format.
            - "gb": Returns data in GenBank format.
          Ensure the chosen `reftype` is compatible with the selected `db`.

        **Returns:**
        On success: Returns the downloaded data as a single raw string with the
        data fetched from Entrez in the specified `reftype`.
        
        **Example Usage:**
        To fetch the FASTA sequence for human TP53 mRNA (NM_000546.6):
        ```
        download_entrez_data(
            ids=["NM_000546.6"],
            db="nucleotide",
            reftype="fasta"
        )
        ```
        

        Same as download_entrez_data but saves the result to a local file instead of returning the content.
        This is useful for large downloads or when you want to persist the data.

        **Parameters:**
        - `ids` (List[str], required): A list of unique identifiers for the records to fetch
        - `db` (DB_LITERAL, required): The target NCBI Entrez database
        - `reftype` (Literal["fasta", "gb"], required): The desired format for the downloaded data
        - `output_path` (Optional[str]): Custom output path. If None, generates unique filename
        
        **Returns:**
        LocalFileResult containing:
        - `path`: Path to the saved file
        - `format`: File format used
        - `success`: Whether the operation succeeded
        - `error`: Error message if failed
        
        **Example Usage:**
        ```
        download_entrez_data_local(
            ids=["NM_000546.6"],
            db="nucleotide",
            reftype="fasta",
            output_path="tp53_sequence.fasta"
        )
        ```