Skip to main content
Glama

Locate an extraction's values on its source pages

datasheetvend_locate_evidence
Read-onlyIdempotent

For every extracted value of an extraction job (one module, or all of them), find the exact words on the source datasheet page the extraction cites and return their box: x, y, width, height normalized 0-1 to the page (origin top-left) plus bounds_pt in PDF points. Each value gets exactly one status: located (its own words boxed, inside or beside the cited snippet), located_value_only (its words occur once on the page and are boxed, but the cited snippet is not on the page), located_snippet_only (the cited snippet boxed, value text not inside it), ambiguous (found more than once, no box guessed), not_found, no_text_layer (a scan), page_unavailable, map_unavailable / map_expired (no document map), no_evidence_page (the output gives no page) or no_value_to_find (the output states no value text and no snippet). box_scope says how tight a box is: 'value' (exactly the value's characters), 'value_estimated' (the value sits inside a longer printed label; its box is estimated from its character offsets, the whole label is in container_boxes), 'label' (could not be narrowed, e.g. vertical text: the whole label is boxed) or 'snippet' (the cited snippet, not the value). matched_text is the text inside the boxes. coverage counts the statuses for the window returned and adds up to targets_returned; page through targets_total with offset / next_offset. Modules without per-value page evidence (kicad, altium and other generated outputs) are listed as not_applicable with the reason. Deterministic: reads the stored output and document map, calls no model. 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>"
    },
    "name": "datasheetvend_locate_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoValues to locate in this answer. Default 50, at most 200.
job_idYesAn extraction job in your account (or shared with it).
moduleNoOne module id, for example 'pinout' or 'absolute_max'. Omit for every module.
offsetNoSkip this many values (from next_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?

Annotations declare readOnly/idempotent/non-destructive, and the description still adds substantial behavior: no model calls, no credit cost, permission scope mirroring the REST API, per-value status enumeration, and not_applicable handling for generated modules. These are exactly the traits an agent cannot get from the annotation flags.

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 the primary action and return shape, then the status catalogue, then scoping/operational notes. It is dense—one long block listing eleven statuses—but nearly every clause carries information an agent needs to interpret results.

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 full burden and does so: it defines box, box_scope values, matched_text, container_boxes, coverage, pagination, and the complete status vocabulary. An agent can interpret any response without further documentation.

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 real meaning: offset pages through targets_total via next_offset, and the module parameter is scoped to per-value page evidence (kicad/altium yield not_applicable). It does not restate limit bounds, which is fine since the schema covers them.

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?

Opens with a specific verb and resource: 'find the exact words on the source datasheet page the extraction cites and return their box' with coordinates and bounds_pt. It is clearly distinguishable from siblings like diagnose_extraction or compare_extractions, which operate on the extraction itself rather than the source pages.

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?

Gives strong context: deterministic, calls no model, costs no credits, needs an API key, and works only on your own, TEAM-shared or PUBLIC jobs. It also states that generated-output modules (kicad, altium) come back not_applicable. It never explicitly names a sibling alternative or a when-not-to-use case, so it stops short of a 5.

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