GetMattered

Draft a Follow-up

getmattered_draft_follow_up

Draft a follow-up message for a job application that has gone quiet, using email, LinkedIn or another channel. Generates a subject and text for review; nothing is sent until you approve it.

Instructions

Write a follow-up message for one application that has gone quiet: the channel it should go through (email, LinkedIn or other), a subject and the text. Pass application_id from getmattered_list_due_follow_ups or getmattered_get_applications. It only drafts: nothing is sent and nothing is recorded. Uses the user's AI credits. Do not use it to send the message; use getmattered_send_follow_up after the user approves the text. Next: show the user the draft, then send an email draft with getmattered_send_follow_up after they say yes.

Input Schema

Name	Required	Description	Default
`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

A4.4/5.0

Behavior5/5

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

Annotations only mark it as non-readonly, non-destructive, non-idempotent; the description goes further by clarifying that despite being a write-kind hint it has no persistence ("nothing is sent and nothing is recorded") and that it consumes the user's AI credits. That credit-cost and no-side-effect disclosure is exactly the context annotations cannot convey.

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

Conciseness3/5

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

The core facts are front-loaded, but the closing sentence ("Next: show the user the draft, then send an email draft with getmattered_send_follow_up...") restates the approval-then-send routing already given two sentences earlier. It also narrows to "an email draft" while the opening allows LinkedIn or other channels, creating mild internal friction.

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 single-parameter drafting tool with an output schema, the description covers purpose, source of the ID, absence of side effects, cost, and the follow-on tool. The only gap is the email-vs-other-channel inconsistency in the final sentence.

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 100% and the single parameter's schema description already states it comes from list_due_follow_ups or get_applications, so the description largely repeats structured data. Baseline 3 applies – no additional constraints or examples are added.

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?

"Write a follow-up message for one application that has gone quiet" states a specific verb and resource, and immediately enumerates the produced artifacts (channel, subject, text). It is clearly separable from getmattered_send_follow_up, which actually transmits the message.

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 gives the preconditions (application must have gone quiet, application_id sourced from getmattered_list_due_follow_ups or getmattered_get_applications), an explicit exclusion ("Do not use it to send the message"), and names the alternative with its trigger condition (after user approval).

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

Deploy Server