Cooper Email

Release idempotency key

cooper_release_idempotency_key

DestructiveIdempotent

Use this after you have confirmed an unknown Idempotency-Key did not send, or you accept the risk of sending again. Requires auth and message_send. Inputs: key (required). Deletes an unknown key, including a stale in_progress row older than the 10 minute lease, so the same key can be reused. Returns {key, released:true}. A done key is HTTP 409 idempotency_key_done and still replays. A fresh in_progress key is HTTP 409 idempotency_request_in_progress. A missing key is HTTP 404 idempotency_key_not_found.

Input Schema

Name	Required	Description	Default
`key`	Yes	Idempotency-Key value to release.

Output Schema

Name	Required	Description
`key`	No	The Idempotency-Key value.
`state`	No	in_progress, done, or unknown.
`endpoint`	No	Endpoint the key was used on.
`inbox_id`	No	Inbox id (inb_…) this object belongs to. Null when it applies to every inbox.
`released`	No	True when the key was released for reuse.
`created_at`	No	ISO-8601 time the object was created.
`expires_at`	No	ISO-8601 time the object expires, or null for no expiry.
`last_error`	No	Last error seen for this key, when any.
`message_id`	No	Message id (msg_…) this result refers to.
`unknown_since`	No	ISO-8601 time the outcome became unknown, when it did.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 3, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "The released key.",
+  "properties": {
+    "created_at": {
+      "description": "ISO-8601 time the object was created."
+    },
+    "endpoint": {
+      "description": "Endpoint the key was used on."
+    },
+    "expires_at": {
+      "description": "ISO-8601 time the object expires, or null for no expiry."
+    },
+    "inbox_id": {
+      "description": "Inbox id (inb_…) this object belongs to. Null when it applies to every inbox."
+    },
+    "key": {
+      "description": "The Idempotency-Key value."
+    },
+    "last_error": {
+      "description": "Last error seen for this key, when any."
+    },
+    "message_id": {
+      "description": "Message id (msg_…) this result refers to."
+    },
+    "released": {
+      "description": "True when the key was released for reuse."
+    },
+    "state": {
+      "description": "in_progress, done, or unknown."
+    },
+    "unknown_since": {
+      "description": "ISO-8601 time the outcome became unknown, when it did."
+    }
+  },
+  "type": "object"
+}

AddedOct 27, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds information the annotations cannot: auth plus message_send scope are required; deletion also clears a stale in_progress row older than the 10 minute lease; and the return is {key, released:true}. It also maps three distinct failure modes to HTTP status codes.

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?

The usage precondition is front-loaded, and the behavioral details follow in descending order of importance. The line 'Inputs: key (required)' is partially redundant with a 100%-documented schema, and the error-code sentence is dense, but neither is filler.

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?

For a single-parameter destructive tool, everything an agent needs is present: preconditions, required scopes, lease semantics, return value, and all documented error outcomes. An output schema exists, yet the inline return note does no harm and makes the description self-contained.

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 a baseline of 3 applies. The description adds real meaning beyond the schema's 'Idempotency-Key value to release': the key must be an unknown key — not a done key and not a fresh in_progress key — which tells the agent when the input is valid.

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 uses a specific verb and resource: it 'deletes an unknown key' so that 'the same key can be reused.' It also distinguishes this tool's domain from adjacent ones: it works on unknown keys, not done keys, and it notes that a done key returns 409 and 'still replays.' That lets an agent tell this apart from resolve_idempotency_key or get_idempotency_key without reading 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 Guidelines5/5

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

It states the trigger conditions explicitly: use this only after confirming that an unknown key did not send, 'or you accept the risk of sending again.' It also gives exclusion cases through the error behavior — a done key is 409 and still replays, while a fresh in_progress key is 409 request_in_progress. When to call and when the call will fail are both covered.

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

All Cooper Email 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.