Skip to main content
Glama

Ask a web page a question, with verified quotes

web_read
Read-only

AI question answering over one live web page or document URL: an answer drawn only from the page text, verbatim quotes with character offsets checked against the page, an answerable flag and low/medium/high confidence. answerable:false (page lacks the answer) is a normal, charged 200 result. Without a question: summary, key points, title. Also final URL, page size, truncation flag. Generated by Anthropic Claude under a fixed Kit Rx prompt; may miss or misstate details. Price: $0.004 per successful call, paid in USDC with x402 v2; failed calls and calls that match nothing are not charged. AI-generated answer; a call with no arguments returns the stored example answer without a model call.

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": "web_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoQuestion to answer from the page, up to 500 characters. Omit it for a summary.
urlYeshttp or https URL of a public page (HTML, or a PDF/DOCX/XLSX document; a bare domain is fetched as https://). Default ports only; credentials, IP addresses, localhost and private or single-label names are rejected.
modeNoanswer (default when q is given: answer, verbatim quotes with offsets, answerable flag, confidence) or summary (default without q: summary, key points, title).
max_charsNoCharacters of the page's main content (as Markdown) read, 1000 to 30000. Default 30000. Longer pages are cut and flagged truncated.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint, and the description goes far beyond them: it discloses that answerable:false is a normal charged 200, that the answer is AI-generated and may miss or misstate details, and that output includes quotes with offsets checked against the page plus a confidence tier. It also spells out the x402 v2 USDC pricing model and which calls are not billed, which is exactly the kind of cost and failure-mode context an agent cannot get from structured fields.

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?

The payload is front-loaded: the first sentence covers inputs, outputs, and verification, and pricing/provenance caveats come last. It is dense and semicolon-chained, so it reads as a wall of clauses rather than clean sections, but nearly every clause carries operational information rather than 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?

There is no output schema, and the description compensates fully by enumerating return fields: answer, verbatim quotes with offsets, answerable flag, confidence, summary/key points/title, final URL, page size, and truncation flag. Given a 4-parameter tool with an open-world fetch and a billing model, an agent has enough to decide, call, and interpret the result.

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 description coverage is 100%, so the schema already explains q, url, mode, and max_chars, including enums and bounds. The description adds only the mode default behavior (answer when q is present, summary otherwise) and repeats truncation, which is baseline-level added value rather than new semantics. Its 'no arguments returns the stored example answer' claim conflicts with url being required, muddying rather than clarifying parameter behavior.

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 opening clause states a specific verb and resource: 'AI question answering over one live web page or document URL,' and the title reinforces it with 'verified quotes.' It is clear what the tool does, but it never positions itself against nearby siblings such as web_answer or web_extract, so an agent comparing candidates gets no routing signal from this text.

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?

Usage is only implied through argument behavior: omit q for a summary, mode defaults follow whether q is present. There is no statement of when this is the right tool versus alternatives, nor any exclusions about page types beyond what the schema already says. The line about a no-argument call returning a stored example is also unusable guidance, since url is required.

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