Skip to main content
Glama

Read one page of an extraction's source datasheet

datasheetvend_read_document_page
Read-onlyIdempotent

Read one page of the source datasheet behind an extraction job as positioned text tokens (text and box in PDF points), in reading windows of at most 1500 tokens (token_offset / next_token_offset). Carries the page's census: text_token_count, vector_path_count, raster_image_count. textless=true means no positioned text (a drawing, a scan, or an old map), not a blank page; payload_elided=true means the page's tokens were dropped to fit the document budget, so read text_token_count. Drawings and images are not served here. Pages are the PDF's physical 1-based pages. Deterministic: reads the stored document map, calls no model and extracts nothing. Costs no credits. Needs a DatasheetVend API key; readable jobs are your own, your workspace's TEAM-shared jobs and PUBLIC jobs, as on the REST API.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "job_id": "<job_id>",
      "page": "<page>"
    },
    "name": "datasheetvend_read_document_page"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageYesPhysical 1-based PDF page number.
job_idYesAn extraction job in your account (or shared with it).
token_limitNoTokens to return. Default 400, at most 1500.
token_offsetNoSkip this many tokens (from next_token_offset). Default 0.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the readOnly/idempotent/non-destructive annotations: declares the operation is deterministic, calls no model, extracts nothing, and costs no credits. It also discloses the authorization scope (own, workspace TEAM-shared, and PUBLIC jobs) and an API key requirement, plus the semantic traps around textless=true and payload_elided=true that would otherwise cause a caller to misread an empty payload.

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?

Purpose is front-loaded and every sentence carries operational information, with no filler or restatement of the title. The middle section is a dense run-on of census flags and edge cases that could be split for faster scanning, though nothing is genuinely wasteful.

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?

With no output schema, the description takes on the full burden of describing the return value and does so: token shape (text and box in PDF points), the page census fields, and the paging cursor. Authorization scope, credit cost, and the non-model/deterministic guarantee round out everything needed to call it correctly.

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 schema already carries each parameter's type, bounds, and defaults. The description still adds real meaning by framing token_offset/token_limit as a reading-window paging mechanism tied to next_token_offset, and by explaining that payload_elided pages require reading text_token_count rather than assuming an empty page.

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?

States a specific verb and resource ('read one page of the source datasheet behind an extraction job') plus the exact return form (positioned text tokens with text and box in PDF points). The clause 'Drawings and images are not served here' carves out the content type, which lets an agent distinguish this from a page-inspection or search sibling without opening any schema.

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

Usage Guidelines4/5

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

Explains the mechanics of use precisely: pages are the PDF's physical 1-based pages, content is served in reading windows of at most 1500 tokens resumed via next_token_offset, and textless/payload_elided flags tell the caller how to react when nothing usable comes back. It does not explicitly name which sibling to call for drawings, images, or keyword lookup, so the alternative routing is only implicit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources