Meetful

Import a transcript

import_transcript

Imports a meeting transcript or chat log from another tool into the signed-in person's Meetful dashboard: .vtt or .srt captions, plain-text transcripts, Read AI JSON, JSON lists of turns, Google Meet and Zoom chat logs, or a WhatsApp export. Speaker labels are kept as written. Returns the new meeting's id and link.

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": {
      "name": "<name>",
      "text": "<text>"
    },
    "name": "import_transcript"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	The file name, with its extension — it says what format this is and often carries the date.
`text`	Yes	The whole file as text.
`title`	No	A title for the meeting, if the file name is not one.
`started_at`	No	ISO 8601 start time, if the file does not say.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare the write profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description need not restate safety. It adds genuinely non-obvious behavior: speaker labels are preserved verbatim, and it returns the new meeting's id and link. It does not address duplicate imports or size limits, which is the remaining gap.

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?

Two sentences, both front-loaded: formats first, then preservation behavior and return value. The long format enumeration is dense but each item is a distinct capability an agent must match against, so it earns its space. Slight compression could be gained by grouping the caption variants.

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 mutation tool with no output schema, the description covers what is created, where it lands, what formats are accepted, and what is returned. Annotations carry the safety profile. Only the repeat-import / deduplication behavior is unaddressed despite idempotentHint=false being 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 coverage is 100%, so name, text, title, and started_at are already documented in the schema, and the baseline of 3 applies. The description's note that speaker labels survive parsing adds a little meaning about how 'text' is processed, but it does not clarify when title or started_at should override file-derived values.

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?

Specific verb plus resource ('Imports a meeting transcript or chat log') with an explicit destination ('signed-in person's Meetful dashboard') and an enumerated set of accepted formats. The read-oriented sibling get_transcript is implicitly distinguished by the import/destination framing, so an agent can tell these apart.

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?

The description effectively says when this tool applies: when content originates from another tool (Read AI, Google Meet, Zoom, WhatsApp) and needs to land in the dashboard. The format list functions as input-selection guidance. It stops short of naming an alternative or stating exclusions, so it is clear context without explicit routing.

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

All Meetful 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?