Skip to main content
Glama

save_watcher

Monitors a web page on a schedule with your browser cookies and notifies you when a custom check detects a change or condition.

Instructions

Watch a page and notify the user when something they care about happens ("tell me when the price drops below 2000", "when results are posted"). The browser fetches the page on a schedule with the user's cookies. mode=fetch (default) loads the URL without rendering it, so point it at the JSON API you found with network_requests when there is one; check is a function body that receives response = { status, url, text, json, contentType } and has no DOM. mode=tab opens the page in a background tab for a moment, for pages built by JavaScript; check runs in the page with full DOM access. check either returns a value (the user is notified when it changes from the last run) or { notify: true/false, message, value }. Notifications go to a browser notification and, with notify including "ntfy", to the user's ntfy topic. Test with run_watcher.

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": {
      "name": "<name>",
      "url": "<url>",
      "check": "<check>"
    },
    "name": "save_watcher"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
modeNo
nameYes
checkYesJavaScript function body. Return a value, or { notify, message, value }.
notifyNoDefault ["browser"].
descriptionNo
every_minutesNoDefault 30, minimum 1.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
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 substantial work: it discloses that the page is fetched on a schedule with the user's cookies, that fetch mode has no DOM while tab mode runs in a live page, how change-detection triggers notifications, and that notifications go to a browser notification plus optionally the user's ntfy topic. It does not say what happens when a name collides with an existing watcher (create vs overwrite), nor how fetch failures or check exceptions are surfaced — meaningful gaps for a persisted, scheduled job.

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-loaded with purpose, then organized by mode, then check contract, then notification delivery, ending with a test pointer — a logical progression. It is dense and long, but nearly every clause adds decision-relevant information; the parenthetical example list is the only mildly expendable part.

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 7-parameter, no-annotation, no-output-schema tool, the description covers the behaviors an agent most needs: scheduling model, cookie-authenticated fetching, mode selection, check contract, and notification routing. Missing pieces are the identity/overwrite semantics of name and error handling for failed 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 only 43%, and the description compensates well for the hard parameters: mode semantics, the check function signature with its exact response shape ({ status, url, text, json, contentType }), the two return styles, and the notify channel values. It leaves name, description, and every_minutes to the schema, and crucially never explains whether name is a unique key that overwrites an existing watcher.

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 — watch a page and notify the user on a condition — with two concrete user-utterance examples that pin down the intent. It is clearly distinguishable from siblings: run_watcher is named as the test path, and list_watchers/delete_watcher are obviously different operations.

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

Usage Guidelines5/5

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

Explicitly routes between the two modes: use mode=fetch against a JSON API discovered via network_requests, and mode=tab for pages built by JavaScript. It also names run_watcher as the way to test before relying on it, which is real when-to-use guidance rather than implication.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.