Skip to main content
Glama
Sign In

callingly

by com.callingly
OverviewDiscussionsAdmin

Add a lead to a follow-up sequence

add_to_sequence
Destructive

Add a lead to an automated follow-up sequence — a voice + SMS series that keeps working the deal until it closes. The lead is enrolled in the given sequence, or the chosen team's sequence when none is given; the team decides who takes the calls. Callingly handles the calls, texts, retries, and timing. Use this to start a persistent follow-up cadence rather than a single call.

Input Schema

NameRequiredDescriptionDefault
emailNoThe lead's email address.
sourceNoWhere this lead came from. Defaults to "MCP".
companyNoThe lead's company name.
team_idYesThe id of the Callingly team (profile) that works the lead. Its follow-up sequence is used when sequence_id is not given.
last_nameNoThe lead's last name.
first_nameNoThe lead's first name.
sequence_idNoThe id of the follow-up sequence to enroll the lead in. Defaults to the team's sequence.
phone_numberYesThe lead's phone number, ideally in E.164 format (e.g. +14155551234).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / sequence_id
      Added value: +{
+  "description": "The id of the follow-up sequence to enroll the lead in. Defaults to the team's sequence.",
+  "type": "integer"
+}
    • changedInput schema / properties / team_id / description
      Previous value: -"The id of the Callingly team (profile) whose follow-up sequence the lead should be added to."New value: +"The id of the Callingly team (profile) that works the lead. Its follow-up sequence is used when sequence_id is not given."
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

The destructiveHint flag only says 'destructive'; the description goes further by disclosing the actual side effects — real outbound calls, texts, retries, and timing run by Callingly and continue until the deal closes. What it omits is how to stop the cadence or what enrollment does to an existing lead record.

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?

Three sentences, front-loaded with the verb and resource, then the mechanics, then the comparison to alternatives. Slight marketing coloring ('keeps working the deal until it closes') but nothing that fails to earn its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter write tool with no output schema, the key questions an agent needs are unanswered: does this create a new lead record or enroll an existing one (create_lead and update_lead are siblings), does re-enrolling duplicate, and what is returned. The description covers the concept well but leaves the calling decision underspecified.

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%, so every parameter is already documented, including the sequence_id defaulting to the team's sequence. The description restates that same fallback rule and adds no new syntax, format, or constraint information, so the baseline 3 applies.

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 and resource (add a lead to a follow-up sequence) and immediately defines what that resource is: a voice + SMS series. It also distinguishes the operation from single-call siblings (schedule_call, make_ai_call) with the closing 'rather than a single call.'

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?

Gives a clear usage cue ('Use this to start a persistent follow-up cadence rather than a single call'), which routes the agent away from the one-off call tools. It does not state exclusions or prerequisites, such as what happens if the lead already exists or whether a lead must be created first.

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

All callingly toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources