Skip to main content
Glama
Sign In

Vendo AI

by com.vendo-ai
OverviewDiscussionsAdmin

Preview launching SDR outreach

sdr_preview_launch_outreach

Dry run of "Save and Launch". Shows the effective settings (request + saved + defaults), contacts in the chosen segment, ready email/LinkedIn contacts, predicted blockers (no LinkedIn account, no own mailbox), the paid-plan rule for managed senders and the delivery window. Nothing is sent. Always call first and show it to the user.

Input Schema

NameRequiredDescriptionDefault
channelsNo
timezoneNoIANA time zone, e.g. Europe/London
branch_idNoCRM branch for replies: a branch id from crm_list_branches, or null/'general' for General
search_idYes
icp_segmentNoWho to contact: fit (Fit + unchecked, default), fit_uncertain, all; legacy: uncertain, unfit, unchecked
work_end_hourNo
work_start_hourNo
exclude_weekendsNo
daily_email_limitNo
email_sender_modeNomanaged = Vendo sender pool (paid plans only); client_owned = the workspace's own connected mailboxes
daily_linkedin_limitNo
client_email_providerNo
selected_linkedin_account_idsNoIds from sdr_get_outreach → linkedin_accounts; empty = every connected account in status OK

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed13 schema fields changed
    • addedInput schema / properties / branch_id
      Added value: +{
+  "description": "CRM branch for replies: a branch id from crm_list_branches, or null/'general' for General",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedInput schema / properties / client_email_provider
      Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "google",
+        "microsoft"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}
    • addedInput schema / properties / daily_email_limit
      Added value: +{
+  "maximum": 500,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / daily_linkedin_limit
      Added value: +{
+  "maximum": 200,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / email_sender_mode
      Added value: +{
+  "description": "managed = Vendo sender pool (paid plans only); client_owned = the workspace's own connected mailboxes",
+  "enum": [
+    "managed",
+    "client_owned"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / exclude_weekends
      Added value: +{
+  "type": "boolean"
+}
    • addedInput schema / properties / icp_segment
      Added value: +{
+  "description": "Who to contact: fit (Fit + unchecked, default), fit_uncertain, all; legacy: uncertain, unfit, unchecked",
+  "enum": [
+    "fit",
+    "fit_uncertain",
+    "all",
+    "uncertain",
+    "unfit",
+    "unchecked"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / search_id / format
      Added value: +"uuid"
    • addedInput schema / properties / selected_linkedin_account_ids
      Added value: +{
+  "description": "Ids from sdr_get_outreach → linkedin_accounts; empty = every connected account in status OK",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • removedInput schema / properties / sender_mode
      Removed value: -{
-  "enum": [
-    "managed",
-    "client_owned"
-  ],
-  "type": "string"
-}
    • addedInput schema / properties / timezone
      Added value: +{
+  "description": "IANA time zone, e.g. Europe/London",
+  "type": "string"
+}
    • addedInput schema / properties / work_end_hour
      Added value: +{
+  "maximum": 23,
+  "minimum": 0,
+  "type": "integer"
+}
    • addedInput schema / properties / work_start_hour
      Added value: +{
+  "maximum": 23,
+  "minimum": 0,
+  "type": "integer"
+}
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and usefully discloses that nothing is sent and what the preview surfaces: effective settings, segment contacts, readiness, blockers, paid-plan rule, and delivery window. It could be stronger by explicitly stating that no persistent changes are saved and by noting any permission prerequisites.

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 front-loaded with the dry-run purpose and uses compact sentences to list the preview outputs and the "nothing is sent" guarantee. It is dense but largely free of waste, though the long output list could be slightly tighter.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter preview tool with no annotations or output schema, the description adequately explains the preview's purpose and high-level outputs. However, it leaves significant gaps around parameter usage and prerequisites, so an agent still needs to lean heavily on the schema to invoke it correctly.

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

Parameters2/5

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

Schema description coverage is only 38% across 13 parameters, so the description needs to compensate for undocumented inputs like search_id, channels, work hours, limits, and client_email_provider. It mentions broad concepts such as "chosen segment" and "delivery window" but does not explain how most parameters affect the preview or what values mean.

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 action and resource: a dry run of "Save and Launch" that shows effective settings, contacts, blockers, and delivery window. "Nothing is sent" clearly distinguishes it from the actual launch sibling and makes the preview purpose unambiguous.

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?

"Always call first and show it to the user" gives clear when-to-use guidance and implies it precedes the real launch. It does not explicitly name sdr_launch_outreach as the alternative or describe when not to use it, but the context is strong.

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

All Vendo AI toolsInspect
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