Skip to main content
Glama

SITEBORNE Utility Network

by net.siteborne
OverviewDiscussionsAdmin

Extract document evidence JSON

siteborne_extract_document_evidence_json
Idempotent

Extract and verify structured evidence from exactly one authorized artifact, prior SITEBORNE upload, or public document URL. Use when: the source of truth is a PDF or supported image and the desired result is evidence JSON. Do not use when: a webpage alone is sufficient (use siteborne_retrieve_verified_web_context), company-wide public evidence is needed (use siteborne_build_company_evidence_graph), or an existing agent response needs evaluation (use siteborne_verify_agent_output). Parameters: provide exactly one reference mode: artifact_reference (an authorized stored artifact), upload_reference (a prior SITEBORNE upload handle, not document bytes) or document_url (a public URL, no credentials). ocr_permission must be true before image-based content is read by OCR, and OCR pages bill at the OCR tier; extraction_request.extract_tables and table_extraction_request request table extraction, and pages with tables bill at the table tier; declared_page_count and page_range are bounded by the page limit below; maximum_authorized_price only constrains payment. Behavior: open-world: a paid request may read governed artifact storage or fetch a public document URL, calls the document provider, and persists payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. This service is currently production-disabled and rejects execution. Economics: upto pricing: the payment challenge authorizes a maximum of $0.19 USD per job; the actual charge is measured per processed page (native-text $0.0098, OCR $0.0156, table $0.0238 per page, the highest applicable tier per page) and never exceeds the authorization. The authorization is a ceiling, not the charge. Documents are limited to 10 pages per job. Failure: schema-invalid input is rejected before any payment challenge; a document over the page limit, an unreadable or encrypted document, or an unavailable provider returns a structured MCP error. Returns: extracted document evidence, integrity/provenance findings, and PCC verification—not an uploaded file.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
page_rangeNoOptional one-indexed inclusive page range to process; both bounds are limited to pages 1 through 10.
document_urlNoPublic document URL for reference mode 3; use exactly one reference mode and never put credentials in this URL.
language_hintsNoUp to five BCP 47 language hints used by OCR and extraction; hints do not translate the document.
ocr_permissionNoExplicit permission to use OCR for image-based content; false prevents OCR even when text is not embedded.
upload_referenceNoPreviously issued SITEBORNE upload handle and declared file metadata for reference mode 2; it does not upload document bytes.
artifact_referenceNoAuthorized stored-artifact descriptor for reference mode 1; use exactly one of artifact_reference, upload_reference, or document_url.
extraction_requestNoSelects text, table, key-value, and buyer-schema extraction outputs; omitted switches retain their documented defaults.
declared_page_countNoOptional declared page count from 1 through 10; enables early scope validation but does not override the observed document.
retention_preferenceNoRequested retention class—none, temporary, or permanent—subject to server policy; it cannot override mandatory retention limits.temporary
maximum_authorized_priceNoBuyer’s decimal-safe maximum authorized price; constrains the payment requirement and not retention or extraction policy.
table_extraction_requestNoExplicit top-level request for table extraction; false leaves tables unrequested.
minimum_verification_scoreNoRequired PCC verification ratio from 0 through 1; raising it makes extracted-evidence acceptance stricter.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYesOutput schema for document_evidence_json.v1 service. Must be a valid PCC 1.0.0 document with required net.siteborne.document-evidence.v1 extension.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.9/5.0
Behavior5/5

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

Annotations (openWorldHint, idempotentHint, readOnlyHint=false) are corroborated and richly extended: the description details the open-world state persistence (payment, audit, job, Workflow), replay protection and no-double-charge semantics, the production-disabled rejection behavior, and the full payment-required flow. It adds the payment ceiling-vs-charge distinction and page-tier billing, going well beyond what annotations convey.

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?

Long but information-dense and well-structured with clear labeled sections (Parameters, Behavior, Economics, Failure, Returns). Every sentence carries operational meaning for a complex paid service; the purpose and usage guidance are front-loaded, and there is no filler or repetition of schema text.

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?

For a 12-parameter paid service with nested objects and an output schema, the description is exceptionally complete: it covers purpose, alternatives, reference-mode constraints, side effects, replay/idempotency, production-disabled status, pricing mechanics, page limits, failure modes, and the return shape. Since an output schema exists, the return summary is appropriately brief.

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. The description adds genuine value beyond the schema: it emphasizes the 'exactly one reference mode' constraint, clarifies upload_reference carries a handle 'not document bytes,' and couples parameters to billing tiers (ocr_permission → OCR tier, extract_tables → table tier). The tier-billing coupling is not present in the schema and is materially useful for an agent deciding parameter choices.

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 opens with a specific verb+resource ('Extract and verify structured evidence') and a precise scope ('exactly one authorized artifact, prior SITEBORNE upload, or public document URL'). It explicitly names three sibling tools and the conditions that route to each, so an agent can disambiguate without opening 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?

Provides explicit 'Use when' and 'Do not use when' guidance naming the exact alternatives (siteborne_retrieve_verified_web_context, siteborne_build_company_evidence_graph, siteborne_verify_agent_output) and the selection conditions. Nothing is left to inference.

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

All SITEBORNE Utility Network toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources