Skip to main content
Glama

Get weekly paths digest

get_weekly_paths_digest
Read-only

Get the facts for this workspace's weekly warm-paths recap: how many new warm intro paths were built last week (and the week before, for trend), which accounts they reach, which of those accounts have open CRM deals (stage, amount, close date), who the connectors are, one example path per account with how the two people know each other, people who changed jobs into new accounts, accounts reached for the first time, people newly added to the network, and paths found from LinkedIn posts. All numbers are exact; quote them as returned.

Use when: Use when writing the weekly paths digest, or when asked what new paths, accounts or deals Boomerang surfaced in a given week. Defaults to the last full Monday-to-Monday week in Pacific time; pass week_start (a Monday, YYYY-MM-DD) for another week. Workspace is taken from session context.

Behavior: read_only

workspace_id / user_id are injected from request headers.

Next steps (after this tool succeeds):
  [REQUIRED] [ACTION]: If crm_status is not CRM_STATUS_CONNECTED, do not mention deals or pipeline at all; never guess deal data.

Internal fields — available for follow-up tool calls but do NOT display to the user: `account_id`

Returns by_source[] with fields:

label: Customer-facing name of where the paths came from, e.g. 'Worked together', 'Meetings'. new_paths Returns top_accounts[] with fields: account_id account_name is_icp crm_owner_name: Account owner in the CRM, when synced. Often empty. new_paths: New warm paths into this account this week. best_path: Strongest new path into this account (may be empty when none has reasoning yet). open_deals: Open deals on this account. Only meaningful when crm_status is CRM_STATUS_CONNECTED. Returns top_connectors[] with fields: connector_name new_paths icp_accounts Returns job_moves[] with fields: contact_name new_title: Title at the new employer; may be empty. new_account_name previous_account_name: Employer they left; may be empty. is_icp: New employer matches the workspace ICP. has_open_deal: New employer has an open CRM deal. Only meaningful when crm_status is CRM_STATUS_CONNECTED. new_paths: New warm paths into the new employer this week. Returns new_super_connectors[] with fields: name category: The network group they were added to, as the workspace named it (e.g. Champions, Investors). new_paths: New warm paths through this person this week. accounts_reached: Distinct accounts those paths reach. Returns linkedin_mentions[] with fields: kind: What happened. Describe it in plain words (e.g. 'tagged in a post', 'comments on each other's posts'); never print the enum. connector_name contact_name contact_title account_name is_icp post_url: Link to the post or comment; may be empty. Only link it, never paste raw URLs as text. Also returns pagination info (new_paths, accounts_reached, icp_accounts_reached, connectors).

IMPORTANT: If the response contains more than one record, always present the options to the user and ask them to choose before taking any follow-up action. Do not act on all results automatically.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_weekly_paths_digest"
  }
}

Input Schema

NameRequiredDescriptionDefault
week_startNo
max_accountsNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Adds substantial behavior beyond annotations: read-only operation, workspace/user injection from headers, required next step when CRM is not connected, internal fields not to display, exact-number quoting, and a multi-record handling rule. These are important operational constraints not captured by the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded and organized into purpose, usage, behavior, next steps, and return fields. However, it is very long and repeats the full output schema field list even though an output schema exists, reducing conciseness.

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?

Given the complex output and rich annotations, the description is largely complete: it covers usage, behavior, next steps, and return-field caveats. The main gap is the undocumented max_accounts parameter, but the tool is otherwise callable from the description.

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 description coverage is 0%, so the description must compensate. It explains week_start well (Monday, YYYY-MM-DD, default last full Monday-to-Monday week in Pacific time) but does not explain max_accounts at all, leaving one of two parameters undocumented.

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: get the facts for the workspace's weekly warm-paths recap. It enumerates the exact content (new paths, accounts, deals, connectors, job moves, LinkedIn mentions), so an agent can distinguish it from generic search tools.

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?

Gives clear usage context: use when writing the weekly paths digest or when asked what new paths, accounts, or deals surfaced in a given week. It also explains the default week and how to override it, but does not name alternatives or when-not to use it.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources