Skip to main content
Glama

List Recordings

list_recordings
Read-onlyIdempotent

List recorded meetings from Kontur.Talk, newest first. Filter by title, paginate with limit and offset, and choose fields to include participant details or keep rows compact.

Instructions

Recordings, newest first. Default row: recording_id, title, created_date (ISO-8601, local zone, to the second), created_by, duration, participants_count, participants (≤6; full list via get_recording), status, has_audio. There is no date window here — the recordings endpoint has no date filter, so narrow with query and limit instead. Returns {recordings, count, has_more, next_offset} — the API gives no grand total, so has_more is the only end signal. A requested field the API did not send is simply missing from the row: that means "not in this payload", not "no data at all".

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNopage size.
queryNotitle search (substring, case-insensitive).
fieldsNorow fields to return; omitted → the default set above. description is available here, and so are the bulky comments_count, frame_size, preview_image and qualities blobs.
offsetNohow many to skip (newest first).
participant_fieldsNofields of each participant; omitted → firstname, surname, patronymic, because participants are what inflate a page (measured on meetings at limit=30: 12.4 KB with names, 45.0 KB carrying department/post/ login too). Ask for department, post, login or any other enum value as needed.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

The description adds substantial behavioral context beyond the annotations: default row selection, no date window, pagination end-signal semantics (has_more is the only end signal), and the meaning of missing fields. It also explains API limitations like no grand total. These traits are not inferable from readOnlyHint or idempotentHint, making this genuinely transparent.

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?

The description is moderately long and information-dense, with every sentence providing value. It front-loads the core purpose and default row, then covers edge behaviors. Slightly more concise phrasing could improve readability, but it avoids fluff and is well organized.

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?

Given the tool's complexity (5 optional params) and the presence of an output schema description, the description is thorough: it covers default fields, ordering, pagination, absence of date filter, field omission semantics, and alternatives for full data. It addresses all likely usage questions and edge cases, making it complete for an agent to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Even though schema coverage is 100%, the description adds meaning to the parameters: it explains the default field set, how fields like description and bulky blobs are available, the performance impact of participant_fields (12.4 KB vs 45.0 KB payloads), and the behavior of query as substring case-insensitive search. This goes well beyond the schema's parameter descriptions.

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 clearly states the tool lists recordings, newest first, and specifies the default fields. It differentiates itself from siblings like get_recording and download_recording by focusing on the list operation and pagination behavior, giving it a specific verb and resource.

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

Usage Guidelines4/5

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

It explains there is no date filter and recommends narrowing via query and limit, which is implicit usage guidance. It also points to get_recording for full participant lists, showing when to use an alternative. However, it does not explicitly state 'use this instead of list_meetings' or other exclusions, so the guidance is mostly about internal limitations rather than comparisons with all siblings.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mainpart/ktalk-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server