Skip to main content
Glama

Watch a web page for changes

watch_page

Start watching a public page: it is re-read on a schedule and each change is recorded as a diff with the sections that changed. Use it to follow prices, policies, docs or announcements over days. Optional: watch only one part of the page with a CSS selector, track keywords, and receive a webhook POST on change. Returns a watch id for get_watch. Watches end after 30 days.

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": "watch_page"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesPublic http(s) URL of the page.
keywordsNoWords to track; with a webhook, only keyword events are sent.
selectorNoCSS selector of the part to watch: tag, .class, #id, tag.class, or descendants such as 'main .price'.
webhook_urlNohttps URL that receives a JSON POST when the page changes.
interval_minutesNoMinutes between checks (default 360).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / interval_minutes / description
      Previous value: -"Minutes between checks, default 360"New value: +"Minutes between checks (default 360)."
    • changedInput schema / properties / keywords / description
      Previous value: -"Optional words to track; with a webhook, only keyword events are sent"New value: +"Words to track; with a webhook, only keyword events are sent."
    • changedInput schema / properties / selector / description
      Previous value: -"Optional CSS selector of the part to watch: tag, .class, #id, tag.class, descendants separated by spaces (e.g. 'main .price')"New value: +"CSS selector of the part to watch: tag, .class, #id, tag.class, or descendants such as 'main .price'."
    • changedInput schema / properties / url / description
      Previous value: -"Public http(s) URL of the page"New value: +"Public http(s) URL of the page."
    • changedInput schema / properties / webhook_url / description
      Previous value: -"Optional https URL that receives a JSON POST when the page changes"New value: +"https URL that receives a JSON POST when the page changes."
  2. Changed3 schema fields changed
    • addedInput schema / properties / keywords
      Added value: +{
      +  "description": "Optional words to track; with a webhook, only keyword events are sent",
      +  "items": {
      +    "type": "string"
      +  },
      +  "maxItems": 10,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • addedInput schema / properties / selector
      Added value: +{
      +  "description": "Optional CSS selector of the part to watch: tag, .class, #id, tag.class, descendants separated by spaces (e.g. 'main .price')",
      +  "type": "string"
      +}
    • addedInput schema / properties / webhook_url
      Added value: +{
      +  "description": "Optional https URL that receives a JSON POST when the page changes",
      +  "type": "string"
      +}
  3. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false; the description goes well beyond that by disclosing the scheduling model, that changes are stored as section-level diffs, webhook POST delivery, and a hard lifecycle limit ('Watches end after 30 days'). The 30-day expiry and diff-recording behavior are non-obvious traits an agent could not infer from annotations or schema.

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?

Four sentences, front-loaded with the core mechanism, then use cases, then options, then return value and expiration. Dense and purposeful, though the option list slightly overlaps with what the schema already documents.

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 by stating the return value (a watch id consumed by get_watch) and the watch lifetime. For a creation tool with an open-world side effect, the scheduling, delivery and expiry behavior are all covered, so an agent has what it needs to call it correctly.

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 every parameter is already documented; the description only restates the optional features (CSS selector for a page subsection, keyword tracking, webhook on change) without adding syntax or edge-case detail. It adds a small amount of meaning — that keyword events are the only webhook payload — but not enough to exceed the baseline.

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 ('Start watching a public page'), then says exactly what the mechanism does: re-read on a schedule, each change recorded as a diff with changed sections. It also links forward to the sibling that consumes the result ('Returns a watch id for get_watch'), so an agent can tell it apart from one-off reads like read_page.

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?

'Use it to follow prices, policies, docs or announcements over days' gives a concrete when-to-use condition tied to change-over-time monitoring. It does not explicitly state when not to use it (e.g. a single snapshot read), but the 'over days' framing implicitly routes one-off reads elsewhere.

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.