Skip to main content
Glama
miracleweasel

katto-mcp

by miracleweasel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

katto_create_clip

Create a new clip from any time range of a completed job's source video when you need a moment Katto did not pick. Use source-video seconds from the transcript; clips last 3–180 seconds.

Instructions

Create a NEW clip from any time range of a completed job's source video, when the user wants a moment Katto did not pick. start_seconds/end_seconds are SOURCE-video seconds (take them from katto_get_transcript segments); the clip must last 3-180 s. Does NOT use video quota. Limits: at most 10 created clips per video, one clip in preparation at a time (409 'Another clip is being prepared' = wait and retry), and only within 7 days of the job (410 after that: the source is no longer kept). Captions come from the words Katto already timed; has_captions=false means that range had none and the clip renders without captions. Not idempotent: each call queues another clip. Returns expected_clip_index; poll katto_get_clips every 15-30 s until a clip with that clip_index appears.

Input Schema

NameRequiredDescriptionDefault
idYesJob id of a completed job (from katto_create_clip_job).
aspectNoOutput aspect ratio. Omit to keep the job's setting (9:16 by default).
end_secondsYesEnd of the clip, in seconds of the source video. The clip must last 3 to 180 seconds.
auto_reframeNofalse = plain center crop instead of following the speaker. Omit for automatic reframing.
start_secondsYesStart of the clip, in seconds of the SOURCE video (read timestamps from katto_get_transcript).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.1

TDQS

A4.8/5.0
Behavior5/5

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

Annotations cover safety (non-readonly, non-idempotent, non-destructive), and the description adds substantial context beyond them: no video quota consumption, 10-clip-per-video cap, one-at-a-time preparation with 409 retry guidance, the 7-day/410 window, captions source behavior, and the polling return contract. This is exactly the extra behavioral detail annotations cannot carry.

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?

Dense but front-loaded: purpose first, then constraints, then return/poll behavior. Every clause is functional, though the sentence packing the quota, limits, and error codes is long and could be split for readability.

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?

With no output schema, the description must explain returns and it does (expected_clip_index plus the 15-30 s polling loop against katto_get_clips). Combined with the limits and error semantics, an agent has everything needed to call and follow up correctly.

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?

Schema coverage is 100%, so the schema carries the field definitions. The description still adds value by stressing that start_seconds/end_seconds are SOURCE-video seconds (not output) and must span 3-180 s, and by pointing to katto_get_transcript for the values, tying the parameters to a concrete workflow.

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 ('Create a NEW clip') plus its distinguishing scope: a manual time range that Katto did not auto-select. This cleanly separates it from katto_create_clip_job (job setup) and katto_more_clips (auto picks).

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

Usage Guidelines5/5

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

Explicitly states when to use it ('when the user wants a moment Katto did not pick'), where to get inputs (katto_get_transcript segments), and where to go next (poll katto_get_clips). It also enumerates limits and the 409/410 error conditions with the correct response, leaving little to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools