Skip to main content
Glama

SeedViews

See or decide on a video

check_video

Without approve, only reads a video's check and approval state (is the post live on the creator's own account, when it counts as approved). approve: true approves it, which lets the creator be paid from money already collected. approve: false needs reason and sends the video back to the creator. Ask your person before deciding unless they told you not to. A checked video nobody answers within 48 hours counts as approved.

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": {
      "casting_id": "<casting_id>",
      "video_id": "<video_id>"
    },
    "name": "check_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonNoRequired with approve: false: what the creator should change.
approveNotrue approves the video, false sends it back. Leave out to only read.
video_idYesThe video id from get_results.
casting_idYesThe casting id that cast returned.
casting_tokenNoThe casting_token that cast returned when it was called without an API key. Not needed with an API key.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false, destructiveHint=false, openWorldHint=true; the description adds the material consequences the annotations cannot convey — approval releases money already collected, a false decision bounces the video back to the creator and needs a reason, and an unanswered check auto-approves after 48 hours. These are side effects and timing rules an agent must know before calling.

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?

The read-only default is stated first, then each approve value and its consequence, then the human-approval caveat, then the timeout rule — every sentence carries a distinct operational fact with no filler.

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?

There is no output schema and no annotations covering return values, so the description carries that burden itself — it describes exactly what state is read back and what the two decisions cause. For a five-parameter tool with a destructive-adjacent decision, death, nothing material is missing.

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 coverage is 100% and the schema already documents approve, reason, video_id, casting_id, and casting_token, so the baseline is 3. The description does add meaning for 'approve' (payment release vs. return to creator) and reinforces the reason requirement, but it says nothing about casting_token or where casting_id and video_id come from, so it stays at baseline.

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 gives a specific verb-plus-resource ('reads a video's check and approval state') and then enumerates the two decision outcomes of the same tool, so an agent immediately understands this is a single endpoint that both reads and decides. It also names the concrete facts returned (whether the post is live on the creator's own account, when it counts as approved), which is far beyond restating the title.

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?

Usage is spelled out per mode: omit 'approve' to only read, set true to approve, set false to send back, and 'reason' is required in the false case. It also adds an operational precondition ('Ask your person before deciding unless they told you not to'), which is real when-to-use guidance. The only gap is that it never points to a sibling such as pay_creator for the downstream payment step.

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