Skip to main content
Glama
NimbleBrainInc

Granola MCP Server

extract_action_items

Extract action items, TODOs, and next steps from meeting notes in Granola. Target specific meetings by ID or scan multiple meetings by date range and attendees.

Instructions

Extract action items from meeting notes.

Use this when asked for action items, TODOs, or next steps. Can target a single meeting by ID, or scan multiple meetings by date range.

Args: meeting_id: Specific meeting ID to extract from (takes precedence) date_from: Start date (YYYY-MM-DD) for scanning multiple meetings date_to: End date (YYYY-MM-DD) for scanning multiple meetings days: Convenience shortcut: last N days from today person: Filter by attendee name or email (only with date range) ctx: MCP context

Returns: Extracted action items with source meeting context

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
meeting_idNo
date_fromNo
date_toNo
daysNo
personNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
totalYes
action_itemsYes
Behavior4/5

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

No annotations provided, so description carries full burden. Adds valuable behavioral context: meeting_id takes precedence over date ranges, person filter only works with date ranges, and describes return format ('action items with source meeting context'). Missing error handling or rate limit disclosures, but covers key operational logic.

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?

Well-structured with clear Args/Returns sections. Front-loaded with purpose and usage triggers. Given zero schema documentation, the parameter descriptions are necessary and efficient. Slightly formal docstring style is appropriate for the information density required.

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?

Comprehensive coverage of parameter interactions (precedence, mutual exclusivity) despite having an output schema available. Explains return values briefly. Could enhance with edge case behavior (e.g., empty results), but adequately covers the tool's filtering logic and scope.

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?

Excellent compensation for 0% schema description coverage. Documents all 5 parameters with semantic meaning: date formats (YYYY-MM-DD), precedence rules ('takes precedence'), convenience semantics ('shortcut: last N days'), and cross-parameter constraints ('only with date range').

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?

Opens with specific verb ('Extract') and resource ('action items from meeting notes'). Clearly distinguishes from sibling tools like summarize_meetings or get_transcript by focusing specifically on actionable TODOs rather than general content retrieval.

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?

Explicitly states trigger phrases ('when asked for action items, TODOs, or next steps') providing clear selection criteria. Lacks explicit 'when not to use' guidance or named alternatives (e.g., differentiate from summarize_meetings), but the positive guidance is strong.

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/NimbleBrainInc/mcp-granola'

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