Skip to main content
Glama

How accurate is the emotional-timecode algorithm

get_clip_accuracy
Read-only

Honest numbers for Orb Studio's reaction-finding algorithm: precision (of the candidates humans voted on, how many had a real reaction), recall (of human-marked moments, how many the algorithm found), the chance level of a random guess, and the data-fitted thresholds once 30 moments are labeled. Also how many candidates were checked for camera cuts.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_clip_accuracy"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

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

The annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that by defining each metric's meaning (precision as candidate-level, recall as human-moment-level) and disclosing the 30-label precondition, but it does not say what is returned or omitted before that threshold is reached.

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?

A single front-loaded sentence that leads with the outcome ('Honest numbers') and then defines each returned quantity, with no filler. The nested parentheticals for precision and recall are dense but each earns its place by disambiguating the metric denominators.

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 carries the burden of explaining return values, and it does so by defining each metric conceptually, including the camera-cut check count. It does not describe the response shape or how metrics appear when unlabeled data is insufficient, which is a minor gap for a no-parameter read tool.

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?

The tool takes zero parameters, so the schema carries no semantic burden and the baseline of 4 applies. The description does not need to explain any inputs and correctly does not attempt to.

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 names a specific resource — the reaction-finding algorithm's accuracy metrics — and enumerates them (precision, recall, chance level, fitted thresholds, camera-cut candidate count). An agent can tell this is a diagnostics/measurement read, distinct from candidate-finding or queuing siblings. It stops short of naming an alternative tool, so differentiation is by resource alone.

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?

Usage is only implied: mentioning 'the data-fitted thresholds once 30 moments are labeled' signals a precondition before thresholds are meaningful, which is helpful context. There is no explicit statement of when to call this versus siblings, nor any when-not guidance or stated behavior below the 30-label threshold.

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.