Skip to main content
Glama

api

by com.docimprint

Extract Structured Data

document.extract_structured
Read-onlyIdempotent

Extract typed fields from document text using a caller-defined schema. Uses a quality AI model with retry logic. Use when you need specific data points from a document rather than full text. For invoices with known fields, document.parse_invoice (prebuilt schema) may be simpler. For general summarization, use document.summarize instead. Schema format: { "field_name": "type hint or description" } — e.g. { "contract_date": "ISO date", "party_a": "string", "penalty_usd": "number" }. Returns: { data: { : value }, data_cited: { : { value, confidence: "high"|"medium"|"low", citations: [{ quote, paragraphs[] }] } } } Example prompts:

  • "Extract the contract date, parties, and penalty amount from this agreement."

  • "Pull the vendor name, PO number, and total from this document."

  • "Get me all named fields from this form using my custom schema."

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesDocument text to extract from. Obtain via document.extract_text or url.extract. Example: "This Service Agreement is entered into on 2025-03-15 between ACME Corp and Beta Inc..."
schemaYesField map: describe each field you want extracted with a type hint. Example: { "total_usd": "number", "vendor": "string", "invoice_date": "ISO date YYYY-MM-DD" }
max_tokensNoInput length cap (1 token ≈ 4 chars). Default ~2500 tokens. Truncates input, not output. Example: 3000

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataYes
data_citedYes

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint and idempotentHint. Description adds 'Uses a quality AI model with retry logic' and details the return format including confidence levels and citations. No contradictions with annotations.

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?

Description is a single paragraph but well-structured: purpose, usage, schema format, return format, examples. Every sentence adds value. Could be slightly more concise, but overall efficient.

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 (custom schema extraction) and the presence of an output schema, the description covers all critical aspects: purpose, usage context, parameter example, return structure, and behavioral traits. No gaps.

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%, providing the baseline. Description goes beyond by offering concrete examples for the 'schema' parameter format and clarifying 'max_tokens' truncation behavior. Adds meaningful context without redundancy.

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 states 'Extract typed fields from document text using a caller-defined schema.' It specifies the verb (extract), resource (structured data), and distinguishes from siblings like document.parse_invoice and document.summarize.

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?

Explicitly says 'Use when you need specific data points...' and provides alternatives: 'For invoices... document.parse_invoice...' and 'For general summarization, use document.summarize.' This gives clear when-to-use and when-not-to-use guidance.

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

All api toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose, with no overlap. The category prefixes (account, bundle, collection, document, job, receipt, url) and specific action names (get, notarize, verify, create, list, etc.) ensure that an agent can unambiguously select the correct tool for any task.

Naming Consistency5/5

All tools follow a consistent category.action or category.action_noun pattern using snake_case (e.g., bundle.get, collection.add_document, url.translate). No mixed conventions or irregular names, making the pattern predictable and easy to learn.

Tool Count4/5

With 22 tools, the set is somewhat large but each tool addresses a distinct need within a broad domain (evidence management, document AI, collections, URL processing, job tracking, receipts). The count is slightly above the typical well-scoped range but still reasonable given the scope.

Completeness2/5

The tool surface has notable gaps: there is no tool to create or delete an evidence bundle, nor to update collections or bundles. The core workflow of creating a bundle from a document is missing, and the lifecycle is incomplete, which would likely cause agent failures in typical use cases.

Resources