Skip to main content
Glama

Durable poll of a URL until a condition fires (paid, x402)

watch_register

PAID: watch a URL until a condition fires (status, body text, JSON path, any change) or the TTL ends; priced by interval x TTL. Unpaid, it returns the price; pay with x402 (USDC on Base, Solana, Polygon, Arbitrum, Avalanche, Sei or X Layer) in _meta['x402/payment'] and call again. Feedback: POST /feedback (free). Read daily; no individual reply. Price: $0.0100 USDC.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "watch_register"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoAbsolute http:// or https:// URL, at most 2048 UTF-8 bytes. We GET it; the body is never returned to you, only the verdict.
predicateNoThe condition that ends the watch.
storageKeyNoOptional: on a match, the result is also written to /storage under this key for the paying wallet, so a successor process can collect it without knowing the watch id.
ttlSecondsNoHow long to keep watching, 60..604800. Must exceed intervalSeconds, or the watch expires before a second sample exists.
intervalSecondsNoSeconds between polls, 60..86400. Shorter costs more.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedInput schema / required
      Removed value: -[
      -  "url",
      -  "intervalSeconds",
      -  "ttlSeconds",
      -  "predicate"
      -]
  2. Changed1 schema field changed
    • changedInput schema / properties / predicate / properties / type / description
      Previous value: -"What counts as a match. The remaining fields are the ones this type needs; the route returns a free 400 naming any that is missing."New value: +"What counts as a match. The remaining fields are the ones this type needs; the route refuses, naming any that is missing."
  3. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only say it is not read-only, not destructive, and not open-world, which is thin. The description adds real behavior: the priced-by-interval×TTL cost model, the multi-chain USDC payment path, the fact that the fetched body is never returned (only a verdict), and the feedback channel with no individual reply. It stops short of saying what happens on TTL expiry without a match or whether watches can be cancelled.

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?

It front-loads the paid nature and the core action, then compresses payment and pricing into one dense clause each. The run-on pricing/payment sentence is info-heavy but every clause carries distinct information; only the feedback-desk sentence is arguably peripheral to invocation.

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 5-parameter tool with a nested predicate object and no output schema, the description covers cost, payment, and the fact that only a verdict comes back — which is the critical piece. It does not describe the shape of that verdict or the timeout outcome, leaving an agent unsure what a successful paid call actually returns beyond 'a verdict'.

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 baseline is 3; the description goes beyond it by coupling parameters to economics ('priced by interval x TTL', 'shorter costs more') and by flagging the cross-parameter constraint that TTL must exceed the interval. The shorthand list of predicate types also previews the nested object before the schema is read.

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 states a specific verb and resource ('watch a URL until a condition fires') and enumerates the condition classes (status, body text, JSON path, any change) plus the TTL bound. It implicitly separates itself from a one-shot check by emphasizing durability ('keeps watching', 'TTL ends'), but it never names or contrasts a sibling explicitly.

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?

It gives useful operational sequencing for the paid flow (unpaid call returns price, then retry with x402 payment in _meta) and states the pricing formula, so an agent knows how to invoke it end to end. It never says when to prefer this over a single check or a deadman-style watcher, and gives no guidance on choosing an interval/TTL for a given monitoring intent.

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