Skip to main content
Glama

ADS Beast

push_lead_outcomes

Destructive

Write the real outcome of leads back into ADS Beast so the ad platforms learn which leads became sales. Each row names a lead by lead_id, email or phone, and its outcome. dry_run defaults to true and reports what would change without writing; run it first. Unmatched rows are skipped unless create_missing is true. The lead's stage follows the outcome unless update_stage is false.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "rows": "<rows>"
    },
    "name": "push_lead_outcomes"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsYesOutcome rows, for example [{"lead_id": 812, "outcome": "won", "reason": "signed"}]. For outcome paid add value (amount), currency (ISO 4217) and plan, e.g. {"external_lead_id": "u-1", "outcome": "paid", "value": 690, "currency": "UAH", "plan": "Pro"}. Accepted field names and outcome values come from lead_outcome_contract.
dry_runNoTrue reports what would change and writes nothing. False applies the rows.
client_idNoClient the rows belong to. Optional with a key bound to one client - that client is used.
update_stageNoMove a matched lead's pipeline stage to match the outcome, for example to won or lost.
source_systemNoName of the system the outcomes came from, recorded on each row.mcp
create_missingNoCreate a new lead for a row that matches none. Off by default: a typo in an email must not insert a record.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and openWorldHint=true, and the description adds real value on top: the dry-run-first workflow, the default-safe create_missing=false with a stated rationale ('a typo in an email must not insert a record'), and the side effect of moving pipeline stage. It does not cover idempotency, duplicate/conflicting matches, or partial-failure behavior, which matter for a destructive bulk write.

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?

Four short sentences, front-loaded with purpose, then the row shape, then the safety default, then the two behavioral caveats. No filler and no repetition of the schema.

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 destructive, open-world bulk write with no output schema, the description covers purpose, safety defaults, skip semantics, and the stage side effect, and it delegates field vocabulary to lead_outcome_contract. The remaining gap is what a dry_run report or a write response actually contains, which the agent must discover by calling.

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 description coverage is 100%, so the schema already documents every parameter including defaults and the paid-outcome example. The description adds only light framing (rows identify a lead by lead_id, email or phone; dry_run should be run first) beyond what the schema states, 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 ('Write the real outcome of leads back into ADS Beast') plus the business reason (ad platforms learn which leads became sales). It also implicitly distinguishes itself from stage-only tools by noting the stage follows the outcome unless update_stage is false, so an agent can tell it apart from move_lead_stage.

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 explicit operational sequencing ('dry_run defaults to true ... run it first') and states the skip behavior for unmatched rows. It points to lead_outcome_contract for accepted field names and outcome values. It stops short of naming when to prefer a sibling such as move_lead_stage or update_lead for non-outcome edits.

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.