Settled

Read a Watchdog's alerts

settled_watch_alerts

Read-onlyIdempotent

Free. Everything a Watchdog has recorded for its endpoint since a given alert id: each change to status, payability, price or payTo, the endpoint’s state now, and next_since to pass on the next call. Use when: you created a watch with settled_watch and did not give a webhook. Not for: endpoints without a watch (use settled_check). Poll it whenever your agent runs; the endpoint is probed about every 15 minutes.

Input Schema

Name	Required	Description
`limit`	No	Most alerts to return, 1-100 (default 50)
`since`	No	Return alerts with an id above this; pass next_since from your last call, or 0 for all
`watch_id`	Yes	The watch_id returned by settled_watch when the Watchdog was bought

Output Schema

Name	Required	Description
`how`	No	How to poll
`url`	No	The watched endpoint
`more`	No	true when more alerts are waiting
`error`	No	Present only when the call failed or needs another step: an error code such as pass_required, next to the fields that explain it
`alerts`	No	Alerts since the given id, oldest first: each change to status, payability, price or payTo
`status`	No	active or expired
`delivery`	No	webhook or poll
`watch_id`	No	The watch
`expires_at`	No	When the watch ends unless renewed
`next_since`	No	Pass this as since on your next call
`attestation`	No	EIP-191 signature over the answer; verify it with settled_verify or any EVM library
`attested_at`	No	When Settled signed this answer (ISO 8601)
`endpoint_now`	No	The endpoint's state now: status, payability, price, payTo, last probe

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 5, 2026

changedInput schema / properties / watch_id / description

Previous value: -"The watch_id returned when the Watchdog was bought"New value: +"The watch_id returned by settled_watch when the Watchdog was bought"

addedInput schema / properties / watch_id / minLength
```
Added value: +8
```

First observedOct 2, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already cover read-only/idempotent/no-destruction, so the bar is lower. The description adds real operational context: it is free, the endpoint is probed roughly every 15 minutes, and next_since should be passed on the following call. It does not discuss pagination limits or error behavior, keeping it short of a 5.

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?

Front-loaded with 'Free' and what is returned, then Use when and Not for as labeled cues. No filler; every clause carries routing or scheduling information.

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?

Despite an output schema existing, the description still conveys the return shape, the cursor handoff, cost, and polling cadence. For a polling/alert tool with a required watch_id, nothing an agent needs to invoke it correctly is missing.

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 the schema already documents watch_id, since, and limit. The description reinforces the since/next_since round-trip pattern, which is useful, but adds no format or bounds beyond what the schema states. Baseline 3 is appropriate.

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: reading everything a Watchdog recorded for an endpoint, enumerating the exact fields (status, payability, price, payTo) and the cursor field next_since. It explicitly distinguishes from sibling settled_check with a Not for clause.

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?

Gives an explicit precondition (you created a watch with settled_watch and gave no webhook), names the exclusion and its alternative (endpoints without a watch use settled_check), and prescribes the polling cadence. An agent knows exactly when to pick this tool.

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

All Settled 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?