Skip to main content
Glama

Find emotional-timecode candidates in a transcript

find_clip_candidates
Read-only

Send transcript segments with times (Supadata format {text, offset, duration} in ms, or {text, start, duration} in seconds) and get candidate reaction moments by Orb Studio's rules: a pause after a line (main signal), a short punchline, an announced surprise, a question as setup. Nothing is stored. Candidates only — a human must watch and confirm.

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": {
      "segments": "<segments>"
    },
    "name": "find_clip_candidates"
  }
}

Input Schema

NameRequiredDescriptionDefault
to_sNo
limitNo
from_sNo
segmentsYes

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?

Annotations only declare readOnlyHint and openWorldHint=false; the description adds real behavioral context beyond that — 'Nothing is stored' confirms statelessness, and it enumerates the actual heuristics used (pause after a line as the main signal, short punchline, announced surprise, question as setup). It does not say whether results are ranked, scored, or capped by the limit parameter.

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?

Three tightly packed sentences, front-loaded with the action before the format details and the confirmation caveat. The first sentence is dense but every clause carries information; little waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description must convey what comes back — it names the heuristics but not the returned candidate object (timecodes? reasons? ordering?), and the time-window and limit parameters go unexplained. Adequate to attempt a call, but an agent would be guessing about the response and about how to scope the segment set.

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 description coverage is 0%, so the description carries the burden, and it does explain the hardest parameter well: accepted segment shapes ({text, offset, duration} in ms vs {text, start, duration} in seconds). However, from_s, to_s, and limit are never mentioned, leaving three of four parameters undocumented in both schema and description.

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?

States a specific verb and resource — send transcript segments with times, get candidate reaction moments — plus the source of the heuristics (Orb Studio's rules) and the scope limit ('Candidates only — a human must watch and confirm'), which separates it from a downstream clip-prediction step.

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 implied by the input description and by the 'candidates only, a human must confirm' caveat, which signals this is a pre-filtering step. But there is no explicit when-to-use framing, no mention of prerequisites (e.g. needing a transcript first), and no routing to an alternative such as a prediction tool.

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.