Skip to main content
Glama

Extract Data from Document

talonic_extract

Extract structured, schema-validated data from invoices, contracts, and other documents. Returns requested fields with confidence scores.

Instructions

Extract structured, schema-validated JSON from a document. Returns the requested fields with per-field confidence scores.

USE WHEN: the user wants specific fields pulled from an invoice, contract, certificate, statement, form, scan, or PDF. NOT FOR: full text (use talonic_to_markdown) · finding documents (use talonic_search / talonic_filter). BY NAME: if the user names a file, call talonic_search first to get its document_id, then call this. ARGS: a schema is REQUIRED — pass inline schema (JSON Schema, e.g. {type:'object',properties:{vendor_name:{type:'string'}}}) OR a saved schema_id, not both. Provide EXACTLY ONE document source: document_id (cheapest, a workspace doc), file_url (public URL), or file_data+filename (small local files only). RETURNS: data (the JSON), confidence.overall and confidence.fields (treat <0.7 as needs review), document metadata, extraction_id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
file_dataNoBase64-encoded file bytes. Recommended path when the agent already has the file in memory (e.g., the user attached a PDF to the conversation). Pair with `filename` so MIME type can be inferred. Works regardless of where the file lives on disk.
filenameNoOriginal filename including extension, e.g. 'invoice.pdf'. Used to infer MIME type when uploading via `file_data`. Required when `file_data` is provided.
file_pathNoLocal path to a document file. Only works if the MCP server has read access to that path. In sandboxed chat clients (Claude Desktop, Cowork) where uploads land in a host-owned directory, use `file_data` instead.
file_urlNoURL to a document file. The Talonic API fetches it server-side. Use this for documents already on the public web.
document_idNoID of a document already in the workspace, to re-extract with a new schema.
schemaNoInline schema definition. REQUIRED unless `schema_id` is provided. Recommended: full JSON Schema {type:'object', properties:{...}}. Also accepted: flat key-type map {field_name:'string', amount:'number'}. Mutually exclusive with `schema_id`.
schema_idNoID of a saved schema. REQUIRED unless `schema` is provided. Accepts UUID or SCH-XXXXXXXX short id from talonic_list_schemas. Mutually exclusive with `schema`.
instructionsNoNatural-language guidance for the extractor, e.g. 'Focus on the billing section. Amounts are in EUR.'
include_markdownNoInclude OCR-converted markdown in the response alongside structured data.
include_provenanceNoInclude per-field provenance (source_text, section, page) showing where each value was found in the document.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
extraction_idYesStable identifier for this extraction.
request_idNoServer-assigned request ID for support and debugging.
statusYesExtraction status (e.g. 'complete').
documentYesMetadata about the ingested document.
dataYesThe extracted structured data, shape determined by the schema.
schemaNoSchema metadata: which schema was used and how it can be saved.
confidenceNoExtraction confidence. Treat fields below ~0.7 as needing human review.
provenanceNoPer-field source evidence (source_text, section, page). Present only when `include_provenance: true`.
processingNoProcessing metadata: duration, pages processed, region.
linksNoURLs for self, document, and human-readable dashboard view.
markdownNoOCR-converted markdown. Present only when `include_markdown: true`.
costNoPer-call cost and post-call balance, parsed from the X-Talonic-* response headers. `null` for non-extract calls; not always present on legacy clients.
Behavior5/5

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

The description adds rich behavioral context: confidence score threshold (<0.7 needs review), returned metadata and extraction_id, schema requirement, and document source selection trade-offs. Annotations provide readOnlyHint=false and destructiveHint=false; the description explains the side effect (creation of extraction_id) without contradicting annotations.

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 well-structured with bold section headers (USE WHEN, NOT FOR, BY NAME, ARGS, RETURNS). Every sentence adds necessary information without redundancy. It is appropriately sized for a complex tool.

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?

Given the tool's complexity (10 parameters, output schema exists), the description covers all critical aspects: usage context, argument selection, output expectations (confidence, metadata, extraction_id), and constraints. The presence of an output schema offloads return value documentation, and the description complements it well.

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

Parameters5/5

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

Despite 100% schema coverage, the description adds significant value: it explains mutually exclusive parameters (schema vs schema_id, document sources), recommends which source to use based on context, and clarifies practical usage (e.g., file_path only if server has access). This goes beyond the schema descriptions.

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 description clearly specifies the verb 'extract' and the resource 'structured JSON from a document'. It explicitly distinguishes from siblings talonic_to_markdown (full text) and talonic_search/filter (finding documents), providing unambiguous purpose.

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 description includes 'USE WHEN' scenarios (specific fields from invoices, contracts, etc.) and 'NOT FOR' exclusions, plus guidance to call talonic_search first for named files. This explicitly tells the agent when and when not to use the tool.

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/talonicdev/talonic-mcp'

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