Skip to main content
Glama

Assess a datasheet before extracting it

datasheetvend_assess_datasheet
Read-onlyIdempotent

Judge whether a datasheet PDF is likely to extract well BEFORE you spend credits on it. Pass the public https URL of the PDF (datasheetvend_search_component_library returns one as datasheet_pdf_url). It reads up to 25 pages and checks structure deterministically: the text layer (scanned or image-only PDFs extract less reliably), page count, which standard datasheet sections are present (sectionsFound of sectionsChecked), and whether it is a family datasheet naming several packages. REPORT THE VERDICT AS GIVEN (likely_good, likely_partial, unlikely, unknown) and do not talk it up: hard gates only ever lower it. Read out the signals, and state the limitations: this is a structural assessment, never a promise that a module (pinout, thermal, footprint) will succeed. textTruncated and truncatedBy say when the read stopped early, so later sections were not seen. If the document cannot be fetched, say it could not be read; do not guess. Deterministic: no model, no extraction, nothing stored, costs no credits, needs a DatasheetVend API key.

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": {
      "document_url": "<document_url>"
    },
    "name": "datasheetvend_assess_datasheet"
  }
}

Input Schema

NameRequiredDescriptionDefault
document_urlYesThe public https:// URL of the datasheet PDF (over stdio, a local path also works).

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 only declare read-only/idempotent/open-world/non-destructive; the description adds substantial behavior beyond that: 25-page read limit, deterministic no-model no-storage execution, zero credit cost, API key requirement, and the truncated/truncatedBy early-stop signal. It also states failure handling ('say it could not be read; do not guess') and anti-overselling rules for the verdict.

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 purpose and the cost-saving rationale, then the signals, then the limitation caveats. It is fairly long and includes some reporting-policy prose that reads as instruction rather than tool semantics, but nearly every sentence carries information an agent needs.

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 burden of explaining return values, and it does: the four verdict values, sectionsFound/sectionsChecked, and textTruncated/truncatedBy. It also bounds the tool's claims (structural only, not a promise any module will succeed), which is exactly the caveat an agent needs to relay.

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% and there is only one parameter, so the baseline is already met. The description adds real meaning: the URL must be public https (local path over stdio), and it tells the agent where to obtain it (datasheet_pdf_url from the search tool).

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 ('judge whether a datasheet PDF is likely to extract well') plus a clear timing constraint ('BEFORE you spend credits'). This cleanly separates it from the many datasheetvend_extract_* siblings, which produce content rather than a pre-flight verdict.

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 a clear trigger (before spending credits) and points to datasheetvend_search_component_library as the source of the URL via datasheet_pdf_url. It does not explicitly name which extraction tool to run afterwards or when to skip assessment, so it stops short of full when/when-not/alternative routing.

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