Skip to main content
Glama
agentisend

agentisend

Reply to a received email

reply_to_email

Send a threaded reply to a received email, setting In-Reply-To and References and applying the same send checks as a new message.

Instructions

Purpose: reply to one received email. Sets In-Reply-To and References so the conversation threads, and runs every send check a new send runs. NOT for: a new conversation (send_email), or reading the original (get_received_email). The recipient is the first Reply-To address, else the first From address; any other addresses in those headers are left off, so pass them as cc if they should get the reply. from defaults to the address that received it. Returns: the outbound message id and its status. Delivery happens after; get_email has the outcome. Refusals are the same as send_email: domain_not_verified, suppressed_recipient, agent_budget_exceeded. Addresses ending in @simulator.agentisend.com cost nothing. Sending twice is sending twice: pass an idempotency_key and a retry returns the first message id instead of a second email.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "received_id": "<received_id>"
    },
    "name": "reply_to_email"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNoCarbon-copy addresses — one string or a list.
bccNoBlind carbon-copy addresses — one string or a list.
fromNoSender address. Defaults to the address the original mail was delivered to.
htmlNoHTML body. Provide html or text.
textNoPlain-text body. Provide html or text.
subjectNoSubject line. Defaults to Re: plus the original subject.
received_idYesThe id from list_received_emails of the mail you are answering.
idempotency_keyNoYour own key for this action. Retrying with the same key returns the first result instead of doing it twice — send one whenever a retry could double the effect.

Output Schema

NameRequiredDescriptionDefault
idNoIdentifier.
errorNoPresent instead of the fields above when the call was refused: code, message, fix, docs_url, retryable and, when waiting helps, retry_after_seconds.
statusNoThe message status.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A5/5.0
Behavior5/5

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

Goes well beyond annotations: threading via In-Reply-To/References, reuse of send checks, async delivery ('delivery happens after; get_email has the outcome'), the exact refusal set (domain_not_verified, suppressed_recipient, agent_budget_exceeded), simulator cost exemption, and opt-in idempotency behavior. No contradiction with idempotentHint=false — the tool is non-idempotent by default with an opt-in key.

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?

Front-loaded with Purpose, then NOT for, Returns, and Refusals. Every clause carries actionable content — no filler, no restatement of the title. Dense but scannable given the tool's complexity.

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?

An output schema exists so return values need no elaboration beyond the pointer to get_email for delivery outcome. Combined with threading, refusal, idempotency, and recipient-resolution coverage, nothing an agent needs in order to invoke this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 100% (baseline 3), the description adds real semantics the schema omits: how the recipient is resolved from Reply-To/From headers, that extra header addresses are dropped unless passed as cc, the default for 'from', and the retry semantics of idempotency_key.

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?

Opens with a precise verb+resource: 'reply to one received email.' It immediately distinguishes itself from the two nearest siblings by name (send_email for new conversations, get_received_email for reading the original), so an agent can route correctly without opening any 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 states what the tool is NOT for and names the alternative siblings for each excluded case. It also gives concrete selection logic (the recipient is the first Reply-To, else the first From; other addresses must be passed as cc), turning raw parameters into a decision procedure.

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