HeyLead

Overview Schema Source Related Servers Discussions Admin

backfill_inbox

Destructive

Scan your LinkedIn inbox for unreplied prospect messages, classify each one, and send discovery DMs to high-confidence leads. Use dry_run to review classifications before enabling sends, or process already-classified signals directly.

Instructions

Process unreplied LinkedIn inbox messages through the inbound pipeline.

Scans your inbox for conversations where prospects messaged you but
never got a reply. Classifies each message and sends discovery DMs.

Args:
    limit: Max conversations to scan (default 50).
    dry_run: If True (default), only classify — don't send DMs. Set False to send.
    min_confidence: Only send DMs for signals >= this confidence (0.0-1.0).
    send_only: If True, skip inbox scan — process already-classified signals
        directly. Use after a dry_run to avoid re-scanning.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No
`dry_run`	No
`send_only`	No
`min_confidence`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.10.375Sep 18, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false. The description adds value by clarifying the destructive action is sending DMs and provides a dry_run safety mechanism. It does not contradict annotations and discloses the side effect clearly. It omits other behaviors like rate limits, but that is minor given the explicit safety control.

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?

The description is concise, with a clear opening summary followed by a bullet-style argument list. Every sentence earns its place; there is no fluff. The main purpose is front-loaded, and the parameters are logically grouped. It is appropriately sized for 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?

The tool has an output schema, so return values need not be described. The description covers the workflow (scan, classify, send), parameter semantics, and the dry_run/send_only usage pattern. For a tool with side effects and four optional parameters, this is complete. Nothing critical is missing for correct invocation.

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?

Schema coverage is 0%, so the description carries the full burden. It explains each parameter: limit (max conversations), dry_run (classify only, don't send), min_confidence (threshold for sending), and send_only (skip scan, process already-classified signals). This goes beyond the schema's bare names and defaults, making parameter usage unambiguous.

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?

The description states a specific verb ('process'), a specific resource ('unreplied LinkedIn inbox messages'), and a specific outcome ('classifies each message and sends discovery DMs'). It clearly differentiates from siblings like check_replies by focusing on backfilling unreplied conversations. No ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit usage flow: run with dry_run to classify, then set send_only to send without re-scanning. It explains when to use each flag. However, it does not explicitly mention alternatives (e.g., 'use check_replies to just check replies'), so it lacks direct sibling differentiation. Still, the intended use is clear.

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