Replies to a message in an agent mailbox while preserving the thread; use it to respond to external recipients without including secrets.
Reply to a message in an agent mailbox, keeping the thread. The recipient is an external party: never include secrets.
| Name | Required | Description | Default |
|---|---|---|---|
| html_body | No | HTML reply | |
| text_body | No | Plain text reply | |
| mailbox_id | Yes | UUID of the agent mailbox | |
| message_id | Yes | UUID of the message to reply to |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It usefully discloses that replies stay in-thread and that the recipient is an external party (a real safety constraint: never include secrets), but says nothing about delivery behavior, failures on invalid message_id, or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, front-loaded with the action and scope, then a safety caveat. Nothing wasteful or repetitive.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple four-parameter send-style tool with a fully described schema and no output schema, the description is adequate but thin: it omits any statement about what a reply produces (new message id, thread linkage) or failure modes, which matter for a mutation tool with no annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all four parameters are already documented in the schema. The description adds only contextual meaning ('recipient is an external party') rather than any syntax or format guidance beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource: reply to a message in an agent mailbox, with the qualifier 'keeping the thread' that separates it from the sibling send_email. It doesn't name the alternative, so differentiation is implied rather than explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'keeping the thread' implies when to choose this over send_email, but there is no explicit when/when-not guidance or stated prerequisite (e.g., message_id must exist in the mailbox). Usage is inferable but not spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.