Skip to main content
Glama
adpilot-mcp

adpilot-mcp

Official
by sholaxai

propose_budget_plan

Propose a reallocation of daily ad budgets toward higher-ROAS campaigns using spend-weighted ROAS shrinkage and bounded water-filling. Review the plan first; nothing changes until applied.

Instructions

Propose a reallocation of daily budgets toward higher-ROAS campaigns. Uses spend-weighted ROAS shrinkage and bounded water-filling. Nothing changes until apply_budget_plan is called.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "propose_budget_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNo
maxStepNo
totalDailyNoNew total daily budget. Defaults to the current total.
aggressivenessNo
pauseCriticalAnomaliesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does deliver the single most important behavioral fact: 'Nothing changes until apply_budget_plan is called,' making the dry-run semantics unambiguous. It also discloses the method (spend-weighted ROAS shrinkage, bounded water-filling), but says nothing about what the returned proposal looks like, persistence, or permissions.

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?

Three tight sentences, front-loaded with the purpose, followed by method then safety caveat. No filler or redundant restatement of the tool name.

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

Completeness3/5

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

There is no output schema and no annotations, so the description should at minimum indicate what a returned plan contains and how the tuning parameters shape it. It covers the safety-critical caveat well but leaves return shape and four parameters undocumented, which is thin for a 5-parameter planning tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 20%, with just totalDaily documented, so the description needed to compensate. It does not explain days, maxStep, aggressiveness, or pauseCriticalAnomalies; 'bounded water-filling' hints at maxStep but never connects to it, leaving four of five parameters semantically opaque.

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 ('Propose a reallocation of daily budgets toward higher-ROAS campaigns') and even names the optimization approach. It is clearly distinguishable from the sibling apply_budget_plan, which the description explicitly references as the commit step.

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 closing sentence establishes the preview-then-commit workflow with apply_budget_plan, which tells an agent when to reach for this tool first. It stops short of explicit exclusions (e.g., when not to reallocate, or how this relates to campaign_performance/detect_anomalies).

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