Skip to main content
Glama

webread__watch

Clean structured content from any public web page for AI agents: markdown, text, outline, links, tables, JSON-LD. GET or POST. /watch snapshots a page and detects changes for repeat monitoring. $0.01 per paid call via x402. Free /preview returns a real extraction of YOUR page. Price: $0.01 per call in USDC on Base (eip155:8453), paid with x402 in params._meta["x402/payment"]. HTTP: GET https://api.firstmention.uk/s/webread/watch

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": "webread__watch"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYespublic page URL to read
modeNoall|text|markdown|outline|links|images|tables|jsonld
limitNomax characters of main text
same_domain_onlyNolimit links to the same domain

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / limit / description
      Added value: +"max characters of main text"
    • changedInput schema / properties / limit / type
      Previous value: -"number"New value: +"integer"
    • addedInput schema / properties / mode / description
      Added value: +"all|text|markdown|outline|links|images|tables|jsonld"
    • addedInput schema / properties / same_domain_only
      Added value: +{
      +  "description": "limit links to the same domain",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / url / description
      Added value: +"public page URL to read"
    • addedInput schema / required
      Added value: +[
      +  "url"
      +]
  2. Added

TDQS

A3.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does most of it: it discloses cost ($0.01 per paid call), payment rail (USDC on Base, eip155:8453), the exact x402 payment location (params._meta['x402/payment']), the HTTP method and endpoint, and a free preview path. What it does not disclose is statelessness semantics, i.e. how snapshots persist between calls and what a detected change looks like.

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?

The content is crammed into a run-on of clauses with no sentence structure, and the key differentiator (snapshot/change detection) is buried in the middle behind generic family marketing ('Free /preview returns a real extraction of YOUR page'). The pricing and endpoint details are duplicated across two clauses, adding noise rather than clarity.

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

Completeness3/5

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

Cost, payment mechanics, and transport are covered well, which matters for a paid tool. But for a stateful monitoring tool with no output schema, the description never explains how snapshots are stored or keyed between calls, what constitutes a detected change, or what the caller receives on first run versus subsequent runs.

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 four declared parameters are already documented and the baseline would be 3. The description adds meaning beyond the schema by explaining that a payment payload must be supplied in params._meta['x402/payment'], a field that does not appear in the input schema at all, so it compensates for a real gap.

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 capability: '/watch snapshots a page and detects changes for repeat monitoring.' That verb+resource statement is specific and distinguishes it from a plain read. However, the leading sentence ('Clean structured content from any public web page…') describes the whole webread family rather than this tool, so the distinguishing purpose arrives second and could be mistaken for webread__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?

The phrase 'for repeat monitoring' gives an implied when-to-use condition, and 'Free /preview returns a real extraction of YOUR page' hints at a trial path. There is no explicit guidance on when to pick this over webread__read for a one-off fetch, nor any statement of when this tool should not be used.

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