ASPERN: counterparty checks for agents

Be told when the answer about an address changes

monitor_subject

DestructiveIdempotent

Ask to be told when the answer about an address CHANGES. The dimensions are the ones the counterparty check already answers, so this is that same reading on a schedule rather than a second opinion; what it adds is the comparison. The first run records a reading and reports nothing — there is nothing yet to compare against, and a first reading dressed up as news is the thing this avoids. Idempotent per subject: calling it again edits the watch rather than creating a second. An unknown dimension or policy is REFUSED rather than dropped, because a watch that quietly ignores half of what you asked for is worse than no watch. Needs a key. WHY readOnlyHint IS false: this call writes a row in our store on behalf of the caller, so a second identical call is not free of consequence.

Input Schema

Name	Required	Description
`policy`	No	The policy its verdict is read against. An unknown name is refused rather than replaced with a default.
`subject`	Yes	The address to watch.
`dimensions`	No	What to watch. All four if you leave it out. An unknown name is refused, not ignored.

Output Schema

Name	Required	Description
`id`	Yes	The watch, for changing or ending it later.
`meta`	No	How current this answer is and what it was read from: `freshness` and the ages behind it. Present on every answer from this server, whatever the tool.
`says`	No	What this watch will and will not tell you. It reports a CHANGE in what we hold, which is not the same as a change in the world.
`policy`	No	The policy its verdict is read against. Null where the watch names none and the default applies; read `says` for which that is.
`subject`	Yes	The address being watched, read back so a watch cannot be set on the wrong one.
`warnings`	No	Anything the server wants a caller to know about THIS answer before acting on it. Empty is the normal case and is not a guarantee.
`dimensions`	Yes	What is actually being watched, which is what you asked for or all four.
`firstReadingAt`	No	When the comparison baseline was taken. Null means no reading yet, so nothing can be reported as a change.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 15, 2026

addedOutput schema / properties / meta

Added value: +{
+  "description": "How current this answer is and what it was read from: `freshness` and the ages behind it. Present on every answer from this server, whatever the tool.",
+  "type": "object"
+}

addedOutput schema / properties / warnings

Added value: +{
+  "description": "Anything the server wants a caller to know about THIS answer before acting on it. Empty is the normal case and is not a guarantee.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Changed4 schema fields changedSep 29, 2026

addedOutput schema / properties / id / description

Added value: +"The watch, for changing or ending it later."

addedOutput schema / properties / policy / description

Added value: +"The policy its verdict is read against. Null where the watch names none and the default applies; read `says` for which that is."

addedOutput schema / properties / says / description

Added value: +"What this watch will and will not tell you. It reports a CHANGE in what we hold, which is not the same as a change in the world."

addedOutput schema / properties / subject / description

Added value: +"The address being watched, read back so a watch cannot be set on the wrong one."

AddedSep 28, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With readOnlyHint=false, the description goes beyond the annotation by explaining the reason ('this call writes a row in our store'), and it discloses idempotency per subject, auth need ('Needs a key'), first-run silence, and that unknown dimension/policy are refused rather than dropped. The one gap is destructiveHint=true: the description says a repeat call 'edits the watch' but never says what prior watch configuration is overwritten.

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

Conciseness3/5

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

The key statement is front-loaded, but the prose is narrative and carries rhetorical filler ('a first reading dressed up as news is the thing this avoids', 'worse than no watch') and a meta-sentence addressing the annotations directly. Each sentence does carry a distinct behavioral fact, but the phrasing is wordier than the payload requires.

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?

An output schema exists, so return-format explanation is rightly omitted, and the description covers the write semantics, idempotency, refusal behavior, auth, and first-run edge case. It stops short of explaining what a 'change' notification looks like or what destructive overwrite entails, which is the only substantive omission for this tool.

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 description coverage is 100%, so the baseline is 3; the description adds real meaning on top. It clarifies that 'subject' is the idempotency key ('calling it again edits the watch rather than creating a second') and reinforces the refusal semantics for unknown policy/dimension names with a rationale the schema only asserts.

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?

The description states a specific verb+resource: be told when the answer about an address changes over time. It explicitly situates itself against a named sibling, explaining that the dimensions are the ones counterparty_check already answers and that this is 'that same reading on a schedule rather than a second opinion.' An agent can distinguish it from counterparty_check without opening either schema.

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?

It gives clear context for use — scheduled re-reads for change detection, with the alternative (counterparty_check) implied as the same reading taken once. It also flags the first-run behavior ('reports nothing') so the agent isn't surprised. There is no explicit 'do not use this for X' exclusion, but the scheduling framing routes the agent well.

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

All ASPERN: counterparty checks for agents 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?