OpenCityRecord

Read the transcript around a moment

get_transcript_window

Read-onlyIdempotent

The passage of a meeting transcript surrounding a given moment — what was said before and after, with speakers and timestamps. Pass the meeting_id and start_seconds from a search_meetings hit.

WHEN: ALWAYS, before quoting or reasoning from a search_meetings hit. Search returns individual segments, and a segment is often a fragment — one real hit was the entirety of "does not have a contract with FLOC". The answer is in the passage around it, not in the segment. WHEN NOT: To find something, use search_meetings first — this tool has no query and only reads a meeting you already located. For a whole document, use fetch.

Prefer this over fetch for transcripts: fetch truncates at 40,000 characters from the START of a meeting, so on a three-hour council meeting anything after roughly the first hour is missing entirely — including most late-agenda votes.

EXAMPLES: { "meeting_id": "977675c0-...", "around_seconds": 5113 } { "meeting_id": "977675c0-...", "around_seconds": 5113, "before_seconds": 300, "after_seconds": 300 }

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Max segments returned. Default 80.
`meeting_id`	Yes	Meeting UUID, taken from a search_meetings or search_documents hit.
`after_seconds`	No	Seconds of transcript to include after the centre. Default 180 — a little longer than `before`, because the answer to 'what happened here' usually follows the mention.
`around_seconds`	Yes	Elapsed seconds into the meeting to centre the window on — pass the `start_seconds` of the hit you want context for.
`before_seconds`	No	Seconds of transcript to include before the centre. Default 120, max 900.

Output Schema

TableJSON Schema

Name	Required	Description
`window`	Yes	The time range actually covered, after clamping to the meeting.
`segments`	Yes
`city_slug`	Yes
`truncated`	Yes	True when `limit` cut the window short — widen nothing, ask for a narrower range.
`video_url`	Yes	Jumps to the start of this window. Use verbatim — do not invent URLs.
`meeting_id`	Yes
`transcript`	Yes	The window as one readable passage, speaker-prefixed. Quote from this verbatim — do not paraphrase and present it as a quote.
`meeting_url`	Yes	Use this verbatim when citing — do not invent URLs.
`meeting_date`	Yes	Unix seconds, UTC midnight.
`meeting_title`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 14, 2026

TDQS

A4.7/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld, non-destructive, so the safety profile is covered. The description adds real behavioral value annotations cannot carry: search returns fragmentary segments, and fetch truncates at 40,000 characters from the START of a meeting, silently losing late-agenda content. It stops short of describing output shape or any rate limits, but the truncation caveat is exactly the kind of context that prevents a wrong tool choice.

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?

Front-loaded with the one-line definition, then WHEN / WHEN NOT / EXAMPLES in scannable order. The anecdote about the FLOC fragment and the fetch truncation detail both earn their length by justifying the routing rule.

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?

An output schema exists, so return values need not be explained. Combined with annotations, a 100%-covered schema, and explicit routing guidance, everything an agent needs to invoke this correctly is present.

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 baseline is 3, but the description adds the non-obvious mapping that the caller should pass start_seconds from a search_meetings hit as around_seconds, and provides two concrete invocation examples including before/after overrides. That is genuine meaning beyond the schema.

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 — return the transcript passage surrounding a given moment, with speakers and timestamps — and immediately frames it against siblings (search_meetings hits, fetch). An agent can distinguish it from every other sibling without opening a schema.

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?

Explicit WHEN (always, before quoting or reasoning from a search hit) and WHEN NOT (to find something, use search_meetings; for a whole document, use fetch), plus a stated preference rule over fetch with the reason. Alternatives and selection conditions are fully specified.

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

All OpenCityRecord tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?