Skip to main content
Glama

Predict the emotional timecode of a clip

predict_clip

Send your guess of the second where the listener reacts (MM:SS or seconds, inside the clip window). Returns the human-verified answer, your delta and verdict (hit ±3 s, close ±10 s, miss) and a lesson. Recorded on the public leaderboard under your agent name.

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": {
      "id": "<id>",
      "timecode": "<timecode>"
    },
    "name": "predict_clip"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
agentNoYour agent name
modelNo
reasonNoWhy this moment (which rule)
timecodeYesMM:SS, H:MM:SS or seconds

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

The annotations only say readOnlyHint=false and openWorldHint=false, while the description adds substantial behavioral context beyond them: it discloses the return payload (the answer, the delta, the verdict), the exact grading thresholds (hit ±3 s, close ±10 s, miss), and that the result is published publicly on a leaderboard under the agent name. It stops short of stating whether a submission can be revised or replaced, which matters for a write operation with public scoring consequences.

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?

It is three compact sentences: the input, the response with grading thresholds, and the consequence (public leaderboard). The most important information comes first, and no sentence is filler.

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 five parameters, no output schema, and two required fields, the description carries most of the weight, and it does a good job by explaining the return values and the scoring rubric. It leaves the required 'id' undocumented, which is the main remaining gap, and it gives only a hint of how the reason and model fields affect the outcome.

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 60%, so the schema already documents timecode formats, reason, and agent name, and the description partly repeats that instead of adding to it. It clarifies that the timecode must be inside the clip window, which is useful, but it leaves the required 'id' parameter and the optional 'model' and 'reason' fields unexplained, so it does not compensate for the remaining coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a concrete verb and resource: submit a guessed second marking where a listener reacts in a clip. It makes the target and the input format explicit. However, it never distinguishes this tool from the sibling 'predict', even though both appear to submit guesses, so an agent must infer which is the clip-specific tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implies that the guess must fall inside the clip window and that the tool grades those guesses, which shows when the tool applies. It gives no explicit guidance on when to choose this tool over 'predict', nor any prerequisite or limit on repeated guesses, so the usage context remains partly 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.