Skip to main content
Glama
adecubed

gigamail

by adecubed
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

reply_mail

Destructive

Reply to an existing message in its thread. TWO-PHASE, HUMAN-APPROVED: the first call (no request_id) executes nothing — it returns status=approval_required with a preview of exactly what would happen and a request_id.

Instructions

Reply to an existing message in its thread. TWO-PHASE, HUMAN-APPROVED: the first call (no request_id) executes nothing — it returns status=approval_required with a preview of exactly what would happen and a request_id. A human approves out of band (GigaMail console, CLI or Telegram, behind Windows Hello / Touch ID); the second call with that request_id executes the payload that was approved (the approved arguments, not the ones passed the second time). Requests expire (default 15 min); identical pending requests are deduplicated; more than 20 requests/hour per tool are refused (status=rate_limited). Every phase is written to the audit log. FIXED ADDRESSING: the reply goes to the From address of the original message — never to Reply-To, never to addresses written in the body — so a hostile email cannot redirect it. The preview shows replying_to {from, subject} and the body. On execution returns {success, provider_result}. Irreversible once sent.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ccNoCC addresses. The reply still goes only to the From address of the original message; cc adds recipients in copy.
bodyYesPlain-text body of the reply. Only the body: recipient, subject ('Re: ...') and threading are set by GigaMail from the original message; the account signature, if any, is appended and shown in the preview.
folderNoFolder containing the original message (IMAP only; default inbox).inbox
account_idNoAccount to operate on (integer id from list_accounts). Omit or null = the user's active account.
message_idYesMessage id exactly as returned by list_messages / list_unread / search_mail (opaque Graph id for Microsoft accounts, numeric IMAP UID for IMAP accounts). Ids are account-specific: never reuse one across accounts.
request_idNoOmit on the first call. On the first call the tool does NOT execute: it returns status=approval_required, a preview and a request_id. A human must approve that request_id out of band (GigaMail console, `gigamail approvals approve`, or Telegram — all behind Windows Hello / Touch ID). Then call again with the same request_id to execute. The agent cannot approve; repeating the call without approval just returns awaiting_approval.
attachmentsNoFile names to attach, as shown by list_knowledge_files. Same rule as send_mail: only files registered in the account identity.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.2
    • changedInput schema / properties / body / description
      Previous value: -"Plain-text body of the reply. Only the body: recipient, subject ('Re: ...') and threading are set by GigaMail from the original message."New value: +"Plain-text body of the reply. Only the body: recipient, subject ('Re: ...') and threading are set by GigaMail from the original message; the account signature, if any, is appended and shown in the preview."
  2. Changed1 schema field changedv0.4.0
    • addedInput schema / properties / folder
      Added value: +{
+  "default": "inbox",
+  "description": "Folder containing the original message (IMAP only; default inbox).",
+  "title": "Folder",
+  "type": "string"
+}
  3. Changed1 schema field changedv0.3.2
    • addedInput schema / properties / cc
      Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "CC addresses. The reply still goes only to the From address of the original message; cc adds recipients in copy.",
+  "title": "Cc"
+}
  4. Changed5 schema fields changedv0.3.0
    • addedInput schema / properties / account_id / description
      Added value: +"Account to operate on (integer id from list_accounts). Omit or null = the user's active account."
    • addedInput schema / properties / attachments
      Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "File names to attach, as shown by list_knowledge_files. Same rule as send_mail: only files registered in the account identity.",
+  "title": "Attachments"
+}
    • addedInput schema / properties / body / description
      Added value: +"Plain-text body of the reply. Only the body: recipient, subject ('Re: ...') and threading are set by GigaMail from the original message."
    • addedInput schema / properties / message_id / description
      Added value: +"Message id exactly as returned by list_messages / list_unread / search_mail (opaque Graph id for Microsoft accounts, numeric IMAP UID for IMAP accounts). Ids are account-specific: never reuse one across accounts."
    • addedInput schema / properties / request_id / description
      Added value: +"Omit on the first call. On the first call the tool does NOT execute: it returns status=approval_required, a preview and a request_id. A human must approve that request_id out of band (GigaMail console, `gigamail approvals approve`, or Telegram — all behind Windows Hello / Touch ID). Then call again with the same request_id to execute. The agent cannot approve; repeating the call without approval just returns awaiting_approval."
  5. First observedv0.1.3

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare destructive/openWorld/not-idempotent, and the description goes far beyond them: human out-of-band approval behind biometrics, the fact that the approved arguments (not the re-passed ones) execute, audit logging of every phase, and irreversibility once sent. This is exactly the behavioral context a mutation tool needs.

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?

Dense and long, but well structured with front-loaded labels (TWO-PHASE, HUMAN-APPROVED, FIXED ADDRESSING) and no filler sentences — every clause carries operational facts. Slightly heavy for a single description, hence a 4 rather than 5.

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 no output schema, the description names the return shapes ({success, provider_result}, approval_required preview with replying_to{from,subject} and body). For a complex, irreversible, human-gated mutation tool, all information an agent needs to call it correctly is present.

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, but the description adds semantics not in the schema: the request_id field's two-call lifecycle and the critical nuance that the second call ignores newly passed arguments in favor of the approved payload, plus the fixed-addressing rule that overrides cc/body contents. This meaningfully exceeds the schema.

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+resource+context: 'Reply to an existing message in its thread.' This cleanly distinguishes it from the sibling send_mail (new message) and from read_message (read-only). An agent can select it without opening the 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?

Explicitly documents the two-phase flow: first call without request_id returns approval_required and executes nothing; second call with the approved request_id executes. It also names expiry (15 min), dedup of identical pending requests, and the 20/hour rate limit — clear when-and-how-to-use guidance including failure modes.

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

Deploy Server

Other Tools