Skip to main content
Glama
Sign In
gwagent

gwagent

by vcnngr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

gmail_reply

Sends a reply to the sender of a conversation's last message, optionally as a draft, with attachments or extra recipients; requires confirm=true and checks unclear send status before retrying.

Instructions

Reply to the sender of the last message of a conversation (or of message_index).

Send is never repeated blind: when Gmail's reaction to Send is unclear the mail is looked up in Outbox / Sent; if that cannot tell, the op fails with error 'send_state_unknown' and nothing is re-sent (check gmail.list folder='sent' before any retry). A result may carry verified_in='outbox' | 'sent' when the send was confirmed that way.

Requires confirm=true (outward-facing or destructive).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "gmail_reply"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNoAdditional Cc recipients.
toNoAdditional To recipients.
bccNoAdditional Bcc recipients.
bodyNoText written above the quoted message (any Unicode, newlines allowed).
indexNoRow index of the conversation (from gmail.list / gmail.search); omit to use the conversation already open.
queryNoRun this Gmail search first and take `index` from its results.
folderNoOpen this folder/label first and take `index` from it.
confirmNoMust be true: this action is outward-facing or destructive.
draft_onlyNoSave the reply as a draft instead of sending it.
attachmentsNoPaths of files on this computer to attach.
drive_filesNoGoogle Drive files to insert as links: 'name' (found with Drive search) or '/Folder/name' (from My Drive).
message_indexNoAnswer this message of the thread (0 = oldest, numbering of gmail.read) through its own header actions; default: the last message.
expect_subjectNoSafety check: the conversation's subject must contain this text (case-insensitive), otherwise nothing is sent (not_found).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations present, the description carries real weight: it discloses idempotency protection for Send, the 'send_state_unknown' failure mode that prevents blind re-sends, and the verified_in='outbox'|'sent' result field. It does not explain what happens when confirm is omitted or how draft_only changes the flow, but the core safety behavior is unusually well documented.

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?

Three tight sentences, front-loaded with the action, followed by the failure/retry guidance and the confirm requirement. No filler, though the send-safety paragraph could be trimmed slightly without losing meaning.

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?

For a 13-parameter outward-facing mutation with no annotations and no output schema, the description covers the highest-risk gaps: confirmation, idempotency, error code, and result field. Remaining behaviors (draft_only, attachments, expect_subject) are adequately handled by the schema descriptions.

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 13 parameters are already fully documented; baseline is 3. The description only adds the semantic that message_index defaults to the last message, which is a marginal supplement.

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 with precise scope: replying to the sender of the last message (or of message_index) of a conversation. This cleanly separates it from gmail_reply_all and gmail_send without needing to open 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 Guidelines3/5

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

Gives operational context (confirm=true required, check gmail.list folder='sent' before retrying) but never says when to choose this over gmail_reply_all, gmail_forward, or gmail_draft. Routing to sibling tools is left implicit.

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