Skip to main content
Glama
Sign In
Uoink

Uoink

by ryanbiddy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Export cited transcript range

export_cited_range
Read-onlyIdempotent

Export a cited transcript range with verbatim cues, speaker provenance, chapter overlaps, links, and evidence references for citing a selected passage.

Instructions

Export verbatim stored transcript cues with speaker provenance, overlapping chapters, safe links and evidence references. Use after search_clips identifies a passage; use get_citation_map for all citation rows or read_library_resource for an existing resource URI. Select exact cue-aligned bounds or a current excerpt, at most 120 seconds and 200 cues. Returns source/media revisions; refusals include next_step. It does not fetch media or recompute transcription.

Input Schema

NameRequiredDescriptionDefault
endNoRange end in seconds; must equal the last selected cue's end (with start).
startNoRange start in seconds; must equal the first selected cue's start (with end).
video_idYesStable saved-item identifier from a search or capture result; not necessarily a YouTube ID.
excerpt_idNoCurrent excerpt identifier instead of explicit cue-aligned start and end bounds.
media_revisionNoOptional expected media snapshot revision; mismatches return revision_unavailable.
source_revisionNoRevision of the saved source evidence; copy from the packet or retrieval result to detect stale input.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.12.1

TDQS

A4.5/5.0
Behavior4/5

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

The annotations already mark the tool as read-only and idempotent. The description adds the 120s/200-cue limits, that refusals include next_step, that source/media revisions are returned, and that it does not fetch media or recompute transcription. Error modes beyond revision mismatch and the output structure are not detailed.

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?

Five sentences, front-loaded with purpose, then usage, constraints, returns and exclusions. The text is dense but every sentence carries information. The opening list of terms like 'safe links' is somewhat jargony.

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?

For a read-only 6-parameter tool with no output schema, the description covers returns at a high level (revisions, refusals with next_step) and the main constraints. The full shape of the exported payload is left implicit.

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 baseline is 3. The description adds that callers choose either exact cue-aligned bounds or an excerpt, which clarifies that start/end and excerpt_id are alternatives. It also states the size limits, which the schema does not encode.

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?

The description names a specific action and resource: export verbatim stored transcript cues with speaker provenance, chapters, links and evidence references. It also separates the tool from siblings by pointing to get_citation_map for all citation rows and read_library_resource for existing URIs.

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?

It says when to call the tool (after search_clips identifies a passage) and names two alternatives with the condition for each. It also states the limits that govern use: at most 120 seconds and 200 cues.

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