oriiion

Boost Post

boost_post

Destructive

Launch a paid ad boosting a published post. THIS SPENDS MONEY: from the user's prepaid ad wallet (budget + service fee), or billed to their own ad account with no fee when they chose their own ad account with the ads add-on. Always confirm the budget with the user before calling. Use get_boost_recommendations first for suggested settings.

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": {
      "postId": "<postId>",
      "budgetCents": "<budgetCents>",
      "durationDays": "<durationDays>"
    },
    "name": "boost_post"
  }
}

Input Schema

Name	Required	Description	Default
`goal`	No	What the ad optimizes for	engagement
`mode`	No	Leave out to follow the user's own setup: own_account when they chose their own ad account with the ads add-on, otherwise managed. managed: paid from the prepaid wallet incl. service fee. own_account: billed to the user's own connected ad account, no fee (requires the ads add-on)
`postId`	Yes	The published post to boost
`platform`	No	Platform to boost on when the post published to several; defaults to the post's own platform
`targeting`	No	Audience targeting; omit to let the platform decide
`budgetCents`	Yes	Total ad budget in cents (e.g. 30000 = 300 kr). The service fee is added on top of this.
`durationDays`	Yes	How many days the ad runs
`notPoliticalConfirmed`	No	Required for LinkedIn: true only after the user confirmed the ad is not political advertising (LinkedIn requires the confirmation and bans political ads)

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 30, 2026

removedInput schema / properties / mode / default
```
Removed value: -"managed"
```

changedInput schema / properties / mode / description

Previous value: -"managed: paid from the prepaid wallet incl. service fee. own_account: billed to the user's own connected ad account, no fee (requires the ads add-on)"New value: +"Leave out to follow the user's own setup: own_account when they chose their own ad account with the ads add-on, otherwise managed. managed: paid from the prepaid wallet incl. service fee. own_account: billed to the user's own connected ad account, no fee (requires the ads add-on)"

First observedOct 21, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already flag a destructive, non-idempotent, open-world write, but the description adds the critical consequence annotations cannot express: real money is spent, from a prepaid wallet (budget + service fee) or an owned ad account with no fee. The human-confirmation requirement is exactly the behavioral context an agent needs before invoking a spend action.

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?

Front-loaded with the action, then the cost warning, then the confirmation rule and prerequisite — a sensible priority order. The capitalized "THIS SPENDS MONEY" is effective but slightly attention-grabbing packaging rather than pure information density.

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 an 8-parameter destructive mutation with nested targeting and no output schema, the description covers the highest-stakes facts (cost, billing mode, prereq tool, user confirmation). It omits the LinkedIn-only notPoliticalConfirmed requirement and any indication of what a successful boost returns, which slightly weakens completeness.

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% and the schema itself explains mode, budgetCents fee handling, targeting pass-through, and the LinkedIn political confirmation. The description only restates the budget/fee relationship, adding little beyond the structured fields, 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 ("Launch a paid ad boosting a published post") and immediately distinguishes itself from sibling ad tools (create_chatgpt_ad, google_ads_*) by being tied to an existing published post. An agent can tell what this does without opening the schema.

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

Usage Guidelines5/5

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

Gives explicit preconditions: confirm budget with the user, and call get_boost_recommendations first for settings. It also explains which billing mode applies in which situation, so the agent knows the context in which the call is safe.

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

All oriiion tools Inspect

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

Need Help?