SocialShot AI

Create photoshoot batch

create_photoshoot_batch

COSTS MONEY: every successful submission spends real, paid credits from the account's SocialShot balance (about credits_estimated in the result; higher tier / output_quality cost more). Only call it when the user has asked for images to be generated, and check get_account (credits, dailyCap) first. Queues AI product-photoshoot generation for 1-50 publicly reachable product image URLs (one output each) and returns batch_id, total and credits_estimated immediately; poll with wait_for_job or get_job. Identical inputs never charge twice: they reuse an idempotency_key derived from the inputs, so the server replays the ORIGINAL batch (idempotent_replay: true) and no new images are made. Pass force_new: true only when the user explicitly wants a new, separately charged run of the same inputs.

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": {
      "scene_type": "<scene_type>",
      "items": "<items>"
    },
    "name": "create_photoshoot_batch"
  }
}

Input Schema

Name	Required	Description
`pose`	No
`tier`	No	economy (default), standard or premium. Higher tiers cost more credits.
`angle`	No
`items`	Yes	1-50 product images; one output image each.
`backdrop`	No	Studio backdrop colour (default "white").
`defaults`	No	Batch-wide overrides applied to every item.
`lighting`	No
`force_new`	No	Start a new, separately charged batch even though identical inputs ran before. Only on the user's explicit request.
`background`	No	Scene background (default "urban street").
`brand_name`	No
`scene_type`	Yes	studio = clean backdrop; lifestyle = styled scene.
`style_mood`	No
`backdrop_id`	No
`composition`	No
`garment_fit`	No
`aspect_ratio`	No
`logo_enabled`	No
`background_id`	No
`logo_alignment`	No
`output_quality`	No	1k (default), 2k or 4k. Higher costs more credits.
`idempotency_key`	No	Optional. Reuse to safely retry the same request; derived from the inputs if omitted.
`product_category`	No
`include_human_model`	No	On-model shot (default true).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds the facts an agent most needs — that submissions spend real paid credits, how cost scales (tier / output_quality), that requests are queued asynchronously, and how idempotency replay prevents double charges. The only nuance is a mild tension with idempotentHint=false, but the disclosure of replay behavior is more useful than the hint alone.

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?

The cost warning is correctly front-loaded and every sentence carries operational content. It is dense — long parentheticals and stacked clauses — but nothing is filler; tightening the idempotency sentence would improve readability without losing meaning.

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

Completeness5/5

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

Given 23 parameters, nested objects, an async queueing model, and no output schema, the definition supplies exactly the missing pieces: what is charged, what is returned immediately, how to poll, and how retries behave. Nothing needed to invoke it safely and correctly is absent.

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

Parameters4/5

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

Schema coverage is only 43% across 23 parameters, so the description carries real weight, and it does explain the batch items constraint, the cost implications of tier/output_quality, and the exact meaning plus safe-retry semantics of idempotency_key and force_new. Many scene-shaping parameters (pose, lighting, background, composition, logo_*) are left to self-describing names, so coverage of the full surface is incomplete.

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 ('Queues AI product-photoshoot generation'), states exact scope ('1-50 publicly reachable product image URLs, one output each'), and names the return payload ('batch_id, total and credits_estimated'). It also distinguishes itself from the polling siblings ('poll with wait_for_job or get_job'), so an agent can separate queueing from status-checking without opening a 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 an explicit precondition ('Only call it when the user has asked for images to be generated, and check get_account (credits, dailyCap) first'), names the follow-up tools for job status, and states a precise when-not with the override ('Pass force_new: true only when the user explicitly wants a new, separately charged run'). This is the rare case of full when/when-not/alternative coverage.

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

All SocialShot AI 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?