Skip to main content
Glama
EllGree
by EllGree

mail_reply

Reply to an email by finding the parent message in your inbox or outbox, sending the response, and automatically marking the parent as done.

Instructions

Reply to a mail. Finds parent in the CALLER's own inbox or outbox (use mail_send if you need to reply across agents), sends the reply with to = parent.from by default, and auto-flips the parent's status to 'done'. One tool call instead of three.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoOverride recipient. Default = parent.from.
refNo
bodyYes
refsNoExternal links: issue, mr, ticket URLs + depends_on (array of mail ids).
topicNoOptional topic override. Default = parent's topic (same conversation continues). Pass an explicit slug only when forking the subject. Slug for the filename. Letters, digits, dashes; start with alphanum; max 81 chars. Uppercase allowed for ticket prefixes — e.g. 'OXXII-2577-pass-2' or 'fix-nbsp-encoding'.
labelsNo
in_reply_toYesParent mail id (must exist in caller's inbox or outbox).
parent_statusNoStatus to flip parent to. Default 'done'.
initial_statusNoStatus of the new reply mail. Default 'open'.
Behavior4/5

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

No annotations provided, so description carries the full burden. It discloses key behaviors: finding parent, default `to`, auto-flipping parent status to 'done', and consolidating operations. However, it omits error handling and response format.

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

Conciseness5/5

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

Three sentences with essential information front-loaded. No unnecessary words; every sentence contributes to understanding the tool's purpose and usage.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While the description covers purpose and key behaviors, it does not mention the return value or expected output. With no output schema, this is a gap. The tool also has nested objects not described in the tool description.

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 coverage is 67%, so baseline is 3. The description adds value by explaining defaults for `to` and `parent_status`, but does not detail each parameter. Overall, it supplements the schema adequately.

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?

Description clearly states the tool replies to a mail, specifies scoping to caller's inbox/outbox, and distinguishes from sibling `mail_send` for cross-agent replies. It is specific and action-oriented.

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 tells when to use this tool vs `mail_send` for cross-agent replies, and notes it consolidates three operations into one call, providing clear context for selection.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/EllGree/mailbox-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server