Skip to main content
Glama

get_drip

Read-onlyIdempotent

Fetch ONE drip campaign in full: every step with its delay and content, a summary of the audience, and the sending settings. Read-only. The drip object is passed through exactly as the API sends it, in PascalCase, so read drip.Status and drip.BlockedReason before offering the user a pause or resume, and drip.StaffHold before promising anything will send. Each entry of drip.Steps carries StepToken, Name, Delay (Unit and Value) and Content (Subject, Preheader, Blocks); the drip also carries Audience and Settings. The documented field table also lists Trigger (join, existing or both), Settings (Language, SendWindow, ExitOnClick, ExitOnWin, MaxEnrollmentsPerDay and HasTemplate) and Audience (Sources and AcquisitionChannels, plus how many Groups, Lists and Agents are selected — counts, not tokens). One field is absent from that table and was seen on a live drip on 2026-10-13: Origin. Settings.SendWindow limits the hours and days anything goes out. What happens to someone who enters OUTSIDE that window is neither documented nor observed — whether they are enrolled and simply wait, or not enrolled at all — so never tell a user which of the two it will be. Step numbering is NOT consistent across this category: drip.Steps[].Index here is 0-BASED — verified against a live two-step drip on 2026-10-12, not just documented — and so is steps[].Index in fetch_drip_report, while NextStep in fetch_drip_enrollments and the Step on each top_links entry of fetch_drip_report are 1-BASED. Index N is the same step as NextStep N+1. Convert before quoting one against the other, and give the user a step number in one scheme only. Step content comes back with its wildcards unresolved, exactly as written — they look like [FIRST_NAME] and are filled per contact at send time: never show a raw wildcard as if it were the final copy, and never treat one as a typo to fix. Account-gated, and the two sides of this category are gated differently: the reads need only the Drip Marketing module, while pause_drip, resume_drip and remove_drip_contact need Drip Marketing plus Send Message. The gate was NOT observed on the test account, so on a 403 read back which module the API named instead of guessing. Drips are created, edited, activated and deleted ONLY in the Sweeppea app: those actions run a launch checklist (template, sender, 10DLC registration, content screening, plan allowance) that this API deliberately does not reproduce. There is no create endpoint and that is by design, not a gap — the API leaves these writes out on purpose (confirmed by the API maintainer, October 2026) — say so plainly instead of hunting for a workaround, and never propose or invent a tool for it.

Input Schema

NameRequiredDescriptionDefault
drip_tokenYesThe drip campaign token (UUID v4)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Far exceeds the annotations: warns about PascalCase passthrough, read drip.Status/BlockedReason/StaffHold before promising anything, unresolved wildcards, account-gating that differs between reads and writes, and an undocumented SendWindow enrollment behavior that must not be asserted. This is exactly the behavioral context annotations cannot carry.

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 content is valuable but the description is a dense wall of run-on sentences mixing field enumeration, step-numbering rules, wildcard rules, gating, and product-boundary messaging. It is front-loaded reasonably but would benefit from structure and trimming of repeated field lists.

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?

Given no output schema, the description carries the full burden of describing return shape and does so thoroughly, including caveats on undocumented fields. It stops just short of completeness by noting field numbering inconsistently across siblings without a fully clean summary of the field table.

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 (drip_token) is fully documented in the schema as a UUID v4. The description adds no token-specific syntax or format detail, so 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?

Opens with a specific verb+resource+scope: 'Fetch ONE drip campaign in full', then enumerates exactly what is returned (every step with delay and content, audience summary, sending settings). This distinguishes it from fetch_drips (list) and fetch_drip_report (reporting) in the sibling set.

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?

Clearly positions the tool as a single-drip read and repeatedly routes the agent away from wrong actions (no create endpoint, writes only in the Sweeppea app, use pause_drip/resume_drip for state changes). It doesn't explicitly compare against fetch_drips or fetch_drip_enrollments as alternatives, so it stops short of full when-to-use guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources