Skip to main content
Glama

Tabularium Snapshot: fetch

tabularium_snapshot_fetch

Paid ($0.005 USDC on Base, x402). Read a web page as markdown as a person sees it, hidden text flagged, with a signed record. Reads a web page as clean markdown, as a person sees it: hidden text and invisible Unicode are kept out of the text and flagged with a prompt-injection verdict. Also reads PDF, Word and Excel files as markdown. Includes an Ed25519-signed record (final URL, time, status, sha256 of body and text) that verifies offline. Charged only for 2xx pages and documents it can read; refused URLs cost nothing.. Charged only if it succeeds. Call once without payment to get the price, then retry with params._meta["x402/payment"].

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": {
      "url": "<url>"
    },
    "name": "tabularium_snapshot_fetch"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesPublic http(s) page to fetch
max_charsNoMost characters of text to return (default 50000); the signature covers exactly what is returned

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior4/5

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

The annotations are thin (readOnlyHint=false, openWorldHint=true), so the description has to carry the load, and it mostly does: it discloses the fixed price and chain, the exact billing rule, the fact that hidden text and invisible Unicode are stripped and scored, and what the signed record attests to. It never explains why readOnlyHint is false for what reads like a read (presumably the payment side effect), which is the one piece of behavior an agent could misread.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Content is front-loaded with price and purpose, but the text is visibly unedited: 'as a person sees it' appears twice, hidden-text handling is described twice, and the billing rule is stated three times ('refused URLs cost nothing.. Charged only if it succeeds') including a doubled period. A third of the description could be deleted without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter, no-output-schema, open-world fetch tool this covers what an agent needs: accepted document types, return shape (markdown), what gets stripped and flagged, the offline-verifiable signed record, and the full payment handshake. Only the truncation/continuation story beyond max_chars and the shape of the returned signature object are left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already defines url and max_chars, including the note that the signature covers exactly what is returned; the description adds little beyond restating that. The one extra piece of parameter meaning, params._meta["x402/payment"], is mentioned in prose but is not in the schema at all (additionalProperties: false), which is helpful to know yet sits awkwardly outside the declared inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete verb and resource (read a web page / PDF / Word / Excel as markdown) and adds distinguishing traits: prompt-injection verdict, Ed25519-signed record, paid. It does not, however, explicitly contrast itself with the sibling tools tabularium_read / tabularium_head / tabularium_export, so an agent still has to infer why it would pick this over tabularium_read.

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

Usage Guidelines3/5

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

There is real operational guidance for the x402 flow (call once without payment for the price, then retry with params._meta["x402/payment"]) and a billing condition (only charged for 2xx pages and readable documents). What's missing is when to choose this tool over the sibling read/fetch tools, or any note on what kind of URLs are refused, so usage is implied rather than fully framed.

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.