ai-content-drop

estimate_ad_cost

Read-onlyIdempotent

Price a studio job before making it: a finished ad from a brief or storyboard (kind "ad"), a UGC creator video (kind "ugc"), a generated avatar (kind "avatar") or a competitor-ad decode (kind "decode"). Returns the credit lines, the total and a quote_id that generate_ad, generate_ugc_video, generate_avatar and decode_ad require. No account needed. For an ad, quote exactly the fields you will submit.

Input Schema

TableJSON Schema

Name	Required	Description
`kind`	No	Defaults to ad.
`brief`	No	The ad brief: brandName, brandOneLiner, valueProps (1-8 strings), cta, intent, format (an id from list_ad_formats), shotCount (1-5), totalDurationSec (5-20), aspect (9:16 \| 16:9 \| 1:1), language, quality (fast \| premium), modelTier (standard \| cinematic), garmentImageUrl for the try-on formats.
`quality`	No	Lip-sync tier. premium costs more per talking shot. Defaults to the brief's quality, else fast.
`model_tier`	No	cinematic renders on Seedance with director-grade camera work and costs more per shot; needs the brief.
`storyboard`	No	The storyboard returned by write_ad_storyboard, as is or edited. When present it is what renders; the brief is optional alongside it.
`persona_mode`	No	synthetic lets the studio substitute one consistent generated creator for the avatar; exact-avatar (default) keeps the avatar as given.
`needs_avatar_gen`	No	True when the avatar still has to be generated (billed as a line).
`needs_product_gen`	No	True when the product still has to be generated (billed as a line).

Output Schema

TableJSON Schema

Name	Required	Description
`kind`	Yes
`basis`	Yes
`lines`	Yes
`quote_id`	Yes	Signed quote. Pass it to the matching generate_* tool; it fixes the price and makes a retry safe.
`next_step`	Yes
`expires_at`	Yes	ISO time after which the quote is refused.
`credits_total`	Yes	For an ad, the most it can cost; the charge on success is never higher.
`expires_in_seconds`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 30, 2026

changedInput schema / properties / brief / description

Previous value: -"The ad brief: brandName, brandOneLiner, valueProps (1-8 strings), cta, intent, format (an id from list_ad_formats), shotCount (2-5), totalDurationSec (6-20), aspect (9:16 | 16:9 | 1:1), language, quality (fast | premium), modelTier (standard | cinematic), garmentImageUrl for the try-on formats."New value: +"The ad brief: brandName, brandOneLiner, valueProps (1-8 strings), cta, intent, format (an id from list_ad_formats), shotCount (1-5), totalDurationSec (5-20), aspect (9:16 | 16:9 | 1:1), language, quality (fast | premium), modelTier (standard | cinematic), garmentImageUrl for the try-on formats."

AddedSep 11, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint/idempotent/non-destructive, and the description is consistent with that. It adds genuinely new behavior: it returns credit lines plus a total plus a quote_id, states no account is needed, and discloses that the quote_id is a prerequisite for the generator tools. Return-format detail is limited, but the output schema is the better place for that.

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 dense sentences with no filler: purpose, kind taxonomy, and return/contract information, all front-loaded. Every clause carries information the agent needs.

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?

For a read-only estimator with a full output schema, this covers what is needed: what it prices, the output contract, the quote_id dependency, and the no-auth condition. Nothing essential is missing or left to inference.

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 100%, so the baseline is 3; the description still adds value by expanding the meaning of the kind enum values (what 'ad', 'ugc', 'avatar', 'decode' actually price) and by giving submission guidance ('quote exactly the fields you will submit'). It does not add syntax detail beyond the schema for the nested brief/storyboard objects.

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?

The description opens with a specific verb and resource ('Price a studio job before making it') and then enumerates the four job kinds it prices (ad, ugc, avatar, decode). It also names the downstream consumers (generate_ad, generate_ugc_video, generate_avatar, decode_ad), so an agent can place it precisely relative to siblings.

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?

It states the timing ('before making it') and adds the concrete rule 'For an ad, quote exactly the fields you will submit.' That is clear context for when to call it, but it does not address the near-neighbour sibling estimate_credit_cost, which an agent would need to disambiguate between.

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

All ai-content-drop 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.