Skip to main content
Glama

Search the source datasheet of an extraction

datasheetvend_search_document
Read-onlyIdempotent

Find where the source datasheet behind an extraction job says something: every text token containing the term, with its page and its box on the page in PDF points. Use it to check an extracted value against the document, or to find the page to read with datasheetvend_read_document_page. Counts are honest: total_hits with hits_returned, a per-page cap of 20 stated with dropped_hits, and fetch_truncated when the database fetch stopped at its cap. A token is one line of text, so a phrase across lines may not match. Three different refusals: DOCUMENT_MAP_UNAVAILABLE (this job has no document map), DOCUMENT_MAP_EXPIRED (the map passed its retention window: no hits does NOT mean the term is absent) and, for a real answer, zero hits. 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>",
      "query": "<query>"
    },
    "name": "datasheetvend_search_document"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesThe term to find, 2-128 characters, for example 'VDDIO' or 'Absolute Maximum'.
job_idYesAn extraction job in your account (or shared with it).
max_hitsNoHits to return, in page order. Default 50, at most 300.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, and the description still adds real value: honest counts (total_hits vs hits_returned, per-page cap of 20 with dropped_hits, fetch_truncated), the tokenization caveat that a phrase spanning lines may not match, three named refusal modes, no-credit cost, and the API-key plus own/TEAM/PUBLIC access scope. The one soft spot is that the distinction between the per-page cap and max_hits is stated but not fully reconciled.

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?

Front-loaded with purpose and the sibling routing, then truncation semantics, caveats, and error codes. A few clauses are run-on (the 'Three different refusals' sentence mixes error codes with the zero-hit case), but no sentence is filler.

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 carries the return-value burden and does it: hit fields, page/box coordinates, honesty fields, truncation flags, and the error taxonomy are all present. Auth requirements and access scope round out what an agent needs to invoke 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 baseline is 3, but the description adds meaning the schema does not: results come back in page order, the per-page cap of 20 interacts with max_hits, and fetch_truncated signals the fetch-level ceiling. That extra context on truncation behavior is genuinely useful beyond the parameter 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?

States a specific verb and resource ('Find where the source datasheet ... says something') and pins the return shape to text tokens with page and bounding box in PDF points. It explicitly separates itself from datasheetvend_read_document_page, so an agent can choose between search and read without opening either schema.

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?

Gives two concrete use cases ('check an extracted value against the document' or 'find the page to read with datasheetvend_read_document_page') and names the follow-up sibling for that second case. The retrieval-vs-read split is explicit rather than inferred.

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