Skip to main content
Glama

Watch a page for changes

writ_create_monitor

WATCHES a page for changes: Writ checks it on a schedule and fires change_detected when the page, a CSS selector's text, a value read by extract, or a visual zone changes. Returns the monitor_id that writ_wire_monitor connects to an alert, a workflow or an AI task (a price watch takes a threshold there). Without interval the answer is needs_input: this plan's options and a tell_user for the user, nothing created. The page is read first: a sign-in answers needs_persona, a bot check offers use_residential.

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": "writ_create_monitor"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
modeNo
watchNocontent (default) | price (the value must hold a number).
deviceNo
enabledNo
extractNoBrowserless read instead of a selector, e.g. {"from":"html_css","selector":".price"}.
intervalNoHow often: an option id from needs_input ('5m', '1h', '24h') or seconds.
selectorNoCSS selector whose text is watched (unset = whole page / uptime).
zone_textNo
persona_idNo
session_idNo
try_anywayNo
request_urlNo
use_residentialNoCheck through a residential exit (bot walls).
interval_minutesNo
requires_browserNo
residential_countryNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • addedInput schema / properties / device
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / enabled
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / interval_minutes
      Added value: +{
      +  "type": "integer"
      +}
    • addedInput schema / properties / mode
      Added value: +{
      +  "enum": [
      +    "selector",
      +    "visual"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / request_url
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / requires_browser
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / residential_country
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / try_anyway
      Added value: +{
      +  "type": "boolean"
      +}
    • addedInput schema / properties / zone_text
      Added value: +{
      +  "type": "string"
      +}
  2. Changed17 schema fields changed
    • removedInput schema / properties / device
      Removed value: -{
      -  "description": "A linked Writ desktop's agent_id (writ_devices) to act on. Omitted: the desktop this connection chose with writ_devices action='use', if any.",
      -  "type": "string"
      -}
    • removedInput schema / properties / enabled
      Removed value: -{
      -  "description": "Start the monitor enabled (default true).",
      -  "type": "boolean"
      -}
    • changedInput schema / properties / extract / description
      Previous value: -"Browserless alternative to `selector`: a response-extraction spec the check applies to a plain HTTP response: {\"from\":\"json\",\"path\":\"data.price\"} (a JSON/XHR endpoint, with request_url), {\"from\":\"html_css\",\"selector\":\".a-offscreen\"} (the page markup), {\"from\":\"regex\",\"pattern\":\"...\"} (a value in a script/JSON blob). For a value readable without JavaScript (most prices and stock lines), no check opens a browser, so each is cheaper and harder to wall than a `selector`/requires_browser check. Structured data (an endpoint, JSON-LD, a JSON blob) survives a redesign best. Same grammar as api_call response_extractions."New value: +"Browserless read instead of a selector, e.g. {\"from\":\"html_css\",\"selector\":\".price\"}."
    • changedInput schema / properties / interval / description
      Previous value: -"How often to check: an option id from the needs_input answer ('5m', '15m', '1h', '6h', '24h') or a number of seconds (3600). Without it the answer is needs_input: this account's options (checks a day, how long the check allowance lasts, allowed or which plan) and a tell_user asking the user to pick; nothing is created. An interval the plan refuses is refused with the allowed ones; one that runs the allowance out before it renews is created with a `warning`."New value: +"How often: an option id from needs_input ('5m', '1h', '24h') or seconds."
    • removedInput schema / properties / interval_minutes
      Removed value: -{
      -  "description": "Legacy: minutes between checks; `interval` replaces it.",
      -  "type": "integer"
      -}
    • removedInput schema / properties / mode
      Removed value: -{
      -  "description": "'visual' watches the on-screen zone of `selector`'s element (or of `zone_text`) and diffs its pixels, for charts, images, badges, or a value no selector can read.",
      -  "enum": [
      -    "selector",
      -    "visual"
      -  ],
      -  "type": "string"
      -}
    • removedInput schema / properties / persona_id / description
      Removed value: -"Every check carries this persona's live session (kept fresh by the persona's own sign-in), so a login or a bot wall it passed stays passed (writ_personas). Only for a page behind a sign-in: a public page is watched without one, and the answer says when one is needed."
    • removedInput schema / properties / request_url
      Removed value: -{
      -  "description": "With `extract`: the endpoint the value comes from (an XHR the page calls), when it is not `url` itself.",
      -  "type": "string"
      -}
    • removedInput schema / properties / requires_browser
      Removed value: -{
      -  "description": "Render with a real browser (JS) instead of plain HTTP, for JS-rendered/SPA pages and framed pages (framesets/iframes): the check matches the rendered, frame-flattened DOM, and selector validation is deferred to the first browser render instead of a raw-HTML fetch. Omitted, a page the access check could only read in a browser is checked in one.",
      -  "type": "boolean"
      -}
    • removedInput schema / properties / residential_country
      Removed value: -{
      -  "description": "ISO-2 exit country for use_residential (e.g. 'ca'); implies use_residential.",
      -  "type": "string"
      -}
    • changedInput schema / properties / selector / description
      Previous value: -"CSS selector for content-change monitoring; unset = uptime/status monitoring."New value: +"CSS selector whose text is watched (unset = whole page / uptime)."
    • removedInput schema / properties / session_id / description
      Removed value: -"An open writ_browser_use session on this page. The selector is proved there before saving (pinned / switched to a zone); required for mode='visual' or zone_text."
    • removedInput schema / properties / try_anyway
      Removed value: -{
      -  "description": "After a bot-check answer: create it on Writ's servers anyway (a check that meets the bot check reads nothing).",
      -  "type": "boolean"
      -}
    • removedInput schema / properties / url / description
      Removed value: -"URL to monitor (required)."
    • changedInput schema / properties / use_residential / description
      Previous value: -"Check through a residential exit — for sites that wall datacentre traffic (Amazon, marketplaces). A bot check found on the page is answered with this offer, or with the alternatives when the plan cannot pay for one."New value: +"Check through a residential exit (bot walls)."
    • changedInput schema / properties / watch / description
      Previous value: -"'price' also rejects a selector whose text holds no number (it becomes a zone). Default 'content'."New value: +"content (default) | price (the value must hold a number)."
    • removedInput schema / properties / zone_text
      Removed value: -{
      -  "description": "The text the page prints where the value is (e.g. '51,77 EUR', 'Currently unavailable'). Locates the zone when no selector exists.",
      -  "type": "string"
      -}
  3. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: it discloses that the page is read at creation time, the specific needs_input/needs_persona response paths, that nothing is created in the needs_input case, and that price watches defer thresholding to wiring. This tells the agent the side effects and failure modes of a non-idempotent, open-world creation call.

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-loads the core verb and trigger conditions, then the return value, then the conditional response paths — no filler sentences. The telegraphic phrasing ('a sign-in answers needs_persona') is dense but each clause carries distinct information, though the compression costs some readability.

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?

For a 17-parameter creation tool with no output schema, the description covers the creation flow and main return value well, but leaves most optional parameters unexplained and does not describe monitor management afterwards. Roughly adequate, with evident gaps an agent would hit when filling non-default options.

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?

With 17 parameters and only 29% schema coverage the description must do heavy lifting, and it does explain `interval` (option id or implied seconds, absence triggers needs_input), `watch: price` needing a numeric value, `selector` as the watched text, `extract` as an alternative read, and `use_residential` for bot walls. However many parameters (device, enabled, zone_text, try_anyway, request_url, interval_minutes, mode, session_id, persona_id, residential_country) get no meaning from either source.

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 ('WATCHES a page for changes') and enumerates exactly what constitutes a change: whole page, a CSS selector's text, a value read by `extract`, or a visual zone. It also names the follow-up tool (writ_wire_monitor) and the returned monitor_id, so an agent can tell this apart from sibling creation tools without opening a schema.

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 concrete when-to-use branching: omit `interval` and the result is needs_input with plan options plus a tell_user, and a sign-in yields needs_persona while a bot check offers use_residential. It also points to writ_wire_monitor for alerting/workflow wiring. It stops short of stating when to prefer writ_create_http_extraction or writ_browser_act over this monitor, so it is clear context rather than full 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.