Skip to main content
Glama

SeedViews

Start a casting

cast

Start a casting: real creators film the app and post it on their own accounts. With dry_run: true nothing is saved and nobody is contacted; you get who SeedViews will look for, the brief, the opening message (opening_message_preview), the price, the totals and the timeline to show your person. Without dry_run a draft is created and the answer holds pay_url (with an API key, a page that takes the payment with no sign-in): your person must open it to pay before any creator hears about it (creator pay plus 5% is collected up front, anything unused is refunded automatically). Plans: $99 a month up to 30 videos live, $249 up to 100, starting when the first video is live. Without an API key the answer includes casting_token: keep it and pass it to every other tool; it is shown once.

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": {
      "store_url": "<store_url>"
    },
    "name": "cast"
  }
}

Input Schema

NameRequiredDescriptionDefault
briefNoWhat the video should show and say. Leave it out to get a draft written from the store listing.
dry_runNotrue: save nothing, contact nobody, charge nothing; only show what this casting would cost and do.
creatorsNoHow many creators to sign (default 3).
price_usdNoWhat each creator is paid per video, in US dollars (default 25). One price for everyone; creators take it or pass. A higher price gets more yeses.
store_urlYesThe app's App Store or Google Play link. Ask your person if you do not know it.
notify_urlNoOptional https address that gets a signed POST when a person has something to do or something changed (a video or payout awaiting approval with its deadline, a creator signed, the casting paid, opened or closed). If an approval is still waiting about 12 hours before its deadline, video.approval_reminder includes video_id and deadline (and payout_id when waiting on payment). The answer holds notify_secret once: keep it to check each delivery's seedviews-signature header.
looking_forNoWho to look for. Leave it out to use what SeedViews drafts from the store link.
deadline_daysNoDays a creator has from their yes to their last post (default 14).
opening_messageNoThe template of SeedViews' first message to each creator; leave it out to use the one drafted from the app and brief (opening_message in the answer). It must start with "Hi [name], [a line about one of their videos]. ", which SeedViews writes per creator, as it does any other [field] you add. Write [pay] where the pay goes: it is filled from the casting (opening_message_preview shows it). No other amount, no link, at most 700 characters, ending with one easy question.
videos_per_creatorNoVideos each creator posts (default 1).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare non-read-only, non-destructive, and closed-world; the description carries the real behavioral load. It discloses the two-phase flow (draft is inert until pay_url is opened), that creator pay plus 5% is collected up front and unused funds auto-refund, the monthly plan tiers and when billing starts, and that casting_token is shown once and must be preserved. This is exactly the context structured fields cannot express.

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 dry_run contrast is front-loaded and nearly every clause carries information an agent needs (token persistence, pay_url behavior, refunds, previews). It is a single dense paragraph, though, and the pricing plan sentence is the least essential part relative to the calling decision, which keeps it from a 5.

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?

With no output schema and ten parameters including a nested object, the description volunteers the key return fields an agent must handle: pay_url, casting_token, notify_secret, opening_message_preview, price, totals, and timeline. Combined with the auth-dependent branches (with vs. without an API key), nothing essential to invoking this correctly is missing.

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 nonetheless adds cross-parameter meaning the schema lacks, such as the 5% fee on creator pay and automatic refund of the remainder, and it ties dry_run to the returned preview fields. The nested looking_for and opening_message parameters are documented in the schema but get no extra clarification in prose, keeping this below a 5.

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 concrete verb and resource plus a plain-language definition of the outcome: "Start a casting: real creators film the app and post it on their own accounts." An agent immediately knows this kicks off a creator campaign rather than reading results or paying a creator, which distinguishes it from check_video, get_results, pay_creator, and send_offers.

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 a clear decision rule for the main branch: dry_run:true saves nothing and shows the plan/cost, while omitting it creates a draft that requires payment via pay_url before anyone is contacted. It also implies sequencing by stating casting_token must be passed to every other tool. It stops short of naming which sibling to call before or after this one, so it is clear context without explicit alternatives.

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.

Resources