Skip to main content
Glama

kelpo_quote_scene

Quote the reviewed scene in credits (default Normal quality: 5 credits per second, 25 for a 5 s video; HD: 10 and 50 when quality_options lists it) without starting a video or charging. credits gives the balance, videos_5s_left, low, expires_next, buy_url and a message to relay: if insufficient=true (launch_allowed=false) the video cannot be launched until the user buys a pack at buy_url: give the price and the link only, no launch button nor rights question; if low_after=true warn the user before launching; if watermark=true (paid with offered credits: the video carries the Kelpo signature « Vidéo IA · kelpo.app ») relay watermark_message before the yes. Check generation_available before requesting approval to generate. next_step (when present) says what to tell the person; files_not_in_video lists their files this single shot leaves out (a logo: plan_video). rights_confirmation_required lists (uncovered_reference_ids) the files still needing the user's rights declaration; requirements carries the same entries. Arguments: {"path": {"id": ""}, "body": {"version": 3}}

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": {
      "path": "<path>",
      "body": "<body>"
    },
    "name": "kelpo_quote_scene"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes
pathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedInput schema / $defs / QuoteInput
      Removed value: -{
      -  "properties": {
      -    "version": {
      -      "title": "Version",
      -      "type": "integer"
      -    }
      -  },
      -  "required": [
      -    "version"
      -  ],
      -  "title": "QuoteInput",
      -  "type": "object"
      -}
    • addedInput schema / $defs / backend__developer_api__QuoteInput
      Added value: +{
      +  "properties": {
      +    "version": {
      +      "title": "Version",
      +      "type": "integer"
      +    }
      +  },
      +  "required": [
      +    "version"
      +  ],
      +  "title": "QuoteInput",
      +  "type": "object"
      +}
    • changedInput schema / properties / body / $ref
      Previous value: -"#/$defs/QuoteInput"New value: +"#/$defs/backend__developer_api__QuoteInput"
  2. Changed1 schema field changed
    • addedInput schema / properties / body / type
      Added value: +"object"
  3. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Far exceeds the annotations, which only say readOnlyHint=false and destructiveHint=false. The description discloses that nothing is charged or generated, enumerates the exact response fields (credits, videos_5s_left, low, expires_next, buy_url, message), and spells out downstream consequences of each flag including the watermark signature. The readOnlyHint=false annotation is not contradicted — a quote record may still be written — so no conflict is flagged.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is correctly front-loaded, but the body is one dense run-on sentence chaining nested conditionals, and the appended raw Arguments JSON partially duplicates the schema. Nearly every clause carries real operational content, yet the formatting makes it hard to parse at a glance.

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?

With no output schema, the description takes on the burden of return-value documentation and does so thoroughly, covering credits fields, next_step, files_not_in_video, rights_confirmation_required and requirements. It stops short of stating error behavior or what project state qualifies as "reviewed", which leaves a small gap for a tool with nested object inputs.

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 0% and the schema only carries bare titles, so the description must compensate. The trailing "Arguments: {path: {id: <project id>}, body: {version: 3}}" does identify path.id as the project id and pins version to 3, but the meaning of version and the required project state ("reviewed scene") are never explained.

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 and resource ("Quote the reviewed scene in credits") and immediately delimits scope with "without starting a video or charging", which separates it from the generation sibling kelpo_generate. An agent knows this is a non-committal price/eligibility check, not a launch.

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 explicit branch-by-branch guidance: check generation_available before requesting approval, handle insufficient=true by giving price and buy_url only with no launch button, warn on low_after=true, and relay watermark_message before the yes. It never names the sibling that actually launches the video, so the routing to the follow-up tool is left implicit.

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