Skip to main content
Glama

Cooper Email

by com.cooperemail
OverviewDiscussionsAdmin

Update an inbox

cooper_update_inbox
DestructiveIdempotent

Use this when an inbox should stop sending and accepting new mail without deleting the address, threads, or history (for example while a human reviews it or during an incident), when it should start again, when you need to set its display name or metadata, when you need to change inbound screening, or when you need to change send_mode. Requires auth. Inputs: inbox_id (required; inbox id, username, or email), status (optional; active or paused), require_sender_auth (optional boolean), display_name (optional string, or null to clear it), metadata (optional object merged into the current metadata; a null value removes that key), screening (optional; off, observe, or hold), send_mode (optional; direct or approval). At least one of those fields is required. A metadata object allows at most 256 keys, keys of at most 256 characters, and string, number, or boolean values. The stored JSON must be at most 16 KB. Otherwise the call returns HTTP 400 invalid_metadata. screening other than off, observe, or hold returns HTTP 400 invalid_screening. send_mode other than direct or approval returns HTTP 400 invalid_send_mode. Entering approval applies immediately when a verified owner exists and turns POST /messages, reply, reply-all, and forward into a pending draft and emails those owners. No verified owner returns HTTP 409 owner_required and leaves send_mode unchanged. An inbox already in approval can be set back to direct only when it has never had a verified owner. An unsubscribed owner, or a username pinned by an owner-confirmed delete, stays in approval. Leaving approval for direct when a verified owner exists emails those owners and waits until they confirm, including PATCH on an inbox whose username is batch. Opening the confirm link does not change the inbox. The copy stored in the agent inbox does not include the confirm token, and an API key cannot submit that link. off skips scoring and records reason screening_off. observe, the default, stores every message and adds the suspicious label when the heuristic score is 40 or higher. hold stores suspicious mail with the held label, fires message.held instead of message.received, and creates no task. Screening never drops mail. Pausing sets paused_at to now and keeps that timestamp if you pause again. Resuming clears paused_at. Resuming an active inbox changes nothing. A paused inbox still counts toward the plan inbox limit, and existing messages stay readable. Sends return HTTP 403 inbox_paused until status is active. Returns the inbox {id, username, email, display_name, created_at, require_sender_auth, labels, expires_at, status, paused_at, metadata, client_id, screening, send_mode}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusNopaused stops new sends and drops new inbound mail. active resumes the inbox.
inbox_idYesInbox id (inb_…), username, or full email address owned by this key
metadataNoMerged into the current metadata. A null value removes that key. At most 256 keys, keys at most 256 characters, values string number or boolean, serialized at most 16 KB. Otherwise 400 invalid_metadata.
screeningNoInbound prompt-injection screen. off skips scoring and records why. observe labels suspicious mail. hold stores suspicious mail for review and fires message.held. Anything else is 400 invalid_screening.
send_modeNoEntering approval applies immediately when a verified owner exists and holds POST /messages, reply, reply-all, and forward until that owner approves the current content. No verified owner returns HTTP 409 owner_required. An inbox already in approval can return to direct only when it has never had a verified owner. An unsubscribed owner still blocks that switch. Leaving approval for direct emails verified owners and waits for confirmation. Anything else is 400 invalid_send_mode.
display_nameNoFrom display name. Send null to clear it. A blank string also clears it.
require_sender_authNoWhen true, owner or allowlist mail becomes a task only if DMARC passes or DKIM passes and aligns with From.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / send_mode / description
      Previous value: -"Entering approval applies immediately and holds POST /messages, reply, reply-all, and forward until a verified owner approves the current content. Leaving approval for direct emails verified owners and waits for confirmation. Anything else is 400 invalid_send_mode."New value: +"Entering approval applies immediately when a verified owner exists and holds POST /messages, reply, reply-all, and forward until that owner approves the current content. No verified owner returns HTTP 409 owner_required. An inbox already in approval can return to direct only when it has never had a verified owner. An unsubscribed owner still blocks that switch. Leaving approval for direct emails verified owners and waits for confirmation. Anything else is 400 invalid_send_mode."
  2. Changed1 schema field changed
    • addedInput schema / properties / send_mode
      Added value: +{
+  "description": "Entering approval applies immediately and holds POST /messages, reply, reply-all, and forward until a verified owner approves the current content. Leaving approval for direct emails verified owners and waits for confirmation. Anything else is 400 invalid_send_mode.",
+  "enum": [
+    "direct",
+    "approval"
+  ],
+  "type": "string"
+}
  3. Changed1 schema field changed
    • addedInput schema / properties / screening
      Added value: +{
+  "description": "Inbound prompt-injection screen. off skips scoring and records why. observe labels suspicious mail. hold stores suspicious mail for review and fires message.held. Anything else is 400 invalid_screening.",
+  "enum": [
+    "off",
+    "observe",
+    "hold"
+  ],
+  "type": "string"
+}
  4. Changed2 schema fields changed
    • addedInput schema / properties / display_name
      Added value: +{
+  "description": "From display name. Send null to clear it. A blank string also clears it.",
+  "type": "string"
+}
    • addedInput schema / properties / metadata
      Added value: +{
+  "description": "Merged into the current metadata. A null value removes that key. At most 256 keys, keys at most 256 characters, values string number or boolean, serialized at most 16 KB. Otherwise 400 invalid_metadata.",
+  "type": "object"
+}
  5. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description substantially exceeds them: it names HTTP error codes (400 invalid_metadata/invalid_screening/invalid_send_mode, 409 owner_required), explains that approval mode converts sends into pending drafts and emails owners, that pausing blocks sends with 403 inbox_paused while keeping mail readable, and that paused inboxes still count toward the plan limit. This is unusually rich disclosure of side effects and failure modes.

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?

Content is front-loaded with use-cases, then inputs, then error/behavior detail, which is a sensible order, and the closing return-object sentence compensates for the absent output schema. However, the send_mode/approval and screening sections are dense walls of run-on prose with some duplication of the schema, costing clarity for an agent that must parse it quickly.

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 7-parameter, nested-object, mutation tool with no output schema, the description covers every input, the requirement that at least one be supplied, enum consequences, error codes, and the shape of the returned inbox object ({id, username, email, ... send_mode}). Nothing needed to invoke it correctly appears to be missing.

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, but the description adds meaning beyond the schema: metadata merge/removal semantics with concrete limits, the screening outcomes and recorded reason, and the send_mode approval/direct state transitions including the 409 path. It largely restates some schema text, but the added cross-field consequences push it above 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?

The description makes clear this is a field-level mutation of an existing inbox – status, display_name, metadata, screening, send_mode – and explicitly distinguishes itself from deletion ('without deleting the address, threads, or history'), separating it from cooper_delete_inbox. It is slightly weaker on stating the action up front, opening with use-cases rather than a definition, but a competent agent can still identify the tool's job.

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?

The opening enumerates concrete when-to-use triggers (pause during an incident, resume, rename, change screening, change send_mode) and implicitly excludes deletion. Alternatives such as cooper_create_inbox and cooper_delete_inbox are distinguished by the no-delete framing, and preconditions like 'Requires auth' and 'At least one of those fields is required' are stated explicitly.

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

All Cooper Email toolsInspect
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