GetMattered

Send a Follow-up Email

getmattered_send_follow_up

Destructive

Sends an approved follow-up email about a job application through the user's connected Gmail or Outlook, then records it on the application. Use only after the user confirms the exact subject and text.

Instructions

Send a follow-up email about one application from the user's connected Gmail or Outlook, under the user's name, then record it on the application. It sends a real email to the address in to and cannot be undone. Pass application_id, to (the recipient's address as the user gave it, never a guess), subject and body (20 to 4,000 characters, the exact text the user approved). Send only on the user's explicit go-ahead: show the exact subject and text first, then send it only after they say yes to that text. Sending needs a connected Gmail or Outlook; without one, nothing is sent, the user sends it themselves, and you record it with getmattered_record_follow_up. On a timeout or an error, call getmattered_list_sent_follow_ups before sending again. Do not use it to answer an email an employer sent; use getmattered_reply_to_email. Next: getmattered_get_inbox for the employer's answer.

Input Schema

Name	Required	Description
`to`	Yes	The recipient's email address, exactly as the user gave it. Never guess one.
`body`	Yes	The message text, 20 to 4,000 characters: the exact text the user approved.
`subject`	Yes	The subject line the user approved.
`application_id`	Yes	The application, from getmattered_list_due_follow_ups or getmattered_get_applications.

Output Schema

Name	Required	Description
`draft`	Yes	From getmattered_draft_follow_up: the drafted message. Nothing was sent.
`action`	Yes	The operation that ran: list, history, draft, send or record_sent.
`history`	Yes	From getmattered_list_sent_follow_ups: follow-ups already sent, newest first.
`recorded`	Yes	From getmattered_send_follow_up or getmattered_record_follow_up: the follow-up count after it was recorded.
`followUps`	Yes	From getmattered_list_due_follow_ups: applications whose follow-up is due, most urgent first.
`nextCursor`	Yes	From getmattered_list_sent_follow_ups: pass as cursor for the next page. Null on the last page.
`notConfirmed`	Yes	True when the user declined the confirmation and nothing was sent.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.10.2Oct 25, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already flag destructiveHint/openWorldHint, and the description adds the operational detail that matters: it sends a real, irreversible email under the user's name, requires an explicit approval gate, and degrades safely when no mailbox is connected. The timeout-retry and duplicate-send guidance is behavior an agent cannot infer from structured hints.

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 front-loaded — the action and its irreversibility come first, conditions and fallbacks after. Every sentence carries distinct guidance, though the paragraph is long enough that a bulleted separation of prerequisites, exclusions, and retry path would scan faster.

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 explanation, and the description covers the remaining risk surface for a destructive, open-world mutation: consent gating, authentication prerequisite, failure fallback, and next-step routing to getmattered_get_inbox.

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 real semantic constraints: 'to' must be the address as the user gave it, never guessed, and subject/body must be the exact approved text. It reinforces rather than merely repeats the schema on length limits.

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 (send) and resource (follow-up email) plus the side effect of recording it on the application. It explicitly distinguishes itself from getmattered_reply_to_email and getmattered_record_follow_up, so an agent can route correctly without opening a 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?

Gives explicit preconditions (connected Gmail/Outlook, user's explicit go-ahead after showing exact text), an exclusion with the named alternative (do not answer employer emails — use reply_to_email), a fallback path when no mailbox is connected, and a recovery procedure on timeout/error (check list_sent_follow_ups before retrying).

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

Deploy Server