Watch

create-watch

Start watching a URL; checks it on a schedule and records changes. Does one check now to set the baseline; does not notify for the baseline. Give at most one of keyword or condition+threshold, and one of selector or json_path.

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": "create-watch"
  }
}

Input Schema

Name	Required	Description
`url`	Yes	public http(s) page or JSON endpoint
`name`	No	label shown in change summaries
`email`	No	address to email on each change
`regex`	No	narrow the extracted text; first capture group (or whole match) is compared
`keyword`	No	alert when this text appears or disappears (case-insensitive)
`selector`	No	CSS selector to watch just part of an HTML page
`condition`	No	with threshold: alert when the first number found crosses it
`json_path`	No	path into a JSON response, e.g. data.items[0].price
`threshold`	No
`webhook_url`	No	https URL to receive signed change events
`interval_min`	No	minutes between checks, default 60 on free
`idempotency_key`	No	same key replays the first result instead of creating a second watch

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With no annotations present, the description carries the full burden and does well: it discloses the immediate baseline check, that the baseline does not trigger a notification, and that subsequent checks record changes. It omits operational details like default intervals, plan limits, or what identifier is returned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short clauses, front-loaded with purpose followed by the two constraint rules. No filler or restatement of the name.

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 12-parameter creation tool with no output schema or annotations, the description covers what happens on creation and the key parameter interactions. It stops short of return-value behavior (e.g., the watch ID) and any permission or quota context.

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 coverage is 92%, so the schema already defines nearly every parameter. The description's mutual-exclusion rules for keyword/condition+threshold and selector/json_path add genuine meaning the schema cannot express, lifting it slightly above the baseline.

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?

States a specific verb and resource ('Start watching a URL') plus the core effect ('checks it on a schedule and records changes'), which is unambiguous. It does not explicitly contrast itself with siblings like list-watches or get-watch, but the create semantics are unmistakable.

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?

Gives concrete composition rules ('at most one of keyword or condition+threshold, and one of selector or json_path') that steer correct invocation. It offers no guidance on when to choose this tool over alternatives or when to prefer a different change-detection mode.

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

All Watch tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?