Vendo AI

Launch SDR outreach (sends real messages)

sdr_launch_outreach

Launches outreach: real emails and/or LinkedIn invites start in the working window and new contacts keep being picked up. Each newly queued contact costs 5 credits. Managed senders need a paid plan; client_owned needs a connected mailbox. Only after the user approved sdr_preview_launch_outreach.

Input Schema

Name	Required	Description
`channels`	No
`timezone`	No	IANA time zone, e.g. Europe/London
`branch_id`	No	CRM branch for replies: a branch id from crm_list_branches, or null/'general' for General
`search_id`	Yes
`icp_segment`	No	Who to contact: fit (Fit + unchecked, default), fit_uncertain, all; legacy: uncertain, unfit, unchecked
`work_end_hour`	No
`work_start_hour`	No
`exclude_weekends`	No
`daily_email_limit`	No
`email_sender_mode`	No	managed = Vendo sender pool (paid plans only); client_owned = the workspace's own connected mailboxes
`daily_linkedin_limit`	No
`client_email_provider`	No
`selected_linkedin_account_ids`	No	Ids from sdr_get_outreach → linkedin_accounts; empty = every connected account in status OK

Schema Changelog

Changes observed during successful MCP inspections.

Changed15 schema fields changedOct 26, 2026

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 / maximum
```
Added value: +500
```
addedInput schema / properties / daily_email_limit / minimum
```
Added value: +1
```
addedInput schema / properties / daily_linkedin_limit / maximum
```
Added value: +200
```
addedInput schema / properties / daily_linkedin_limit / minimum
```
Added value: +1
```

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"
+}

First observedJul 28, 2026

TDQS

A4.1/5.0

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 does a lot of it: it discloses that real messages are sent, that contacts continue to be picked up over the working window, the credit cost (5 per newly queued contact), and plan/mailbox prerequisites. It does not state whether re-launching an active outreach errors or how limit overruns behave, leaving some mutation risk undisclosed.

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

Conciseness5/5

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

Four short sentences, each carrying distinct information (effect, credits, prerequisites, approval gate), with the action verb front-loaded. Zero filler and no repetition of the title.

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, irreversible, credit-spending mutation with no annotations and no output schema, the description covers the safety-critical facts well but leaves most parameters (recipient selection via search_id/icp_segment, limits, LinkedIn account selection) and the post-call outcome unaddressed. Adequate, not complete.

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 only 38%, and the description compensates partially: "emails and/or LinkedIn invites" clarifies channels, "working window" frames timezone/work_start_hour/work_end_hour/exclude_weekends, and the sender-mode sentence explains managed vs client_owned beyond the schema's own text. However search_id, icp_segment, branch_id, the daily limits, and selected_linkedin_account_ids are never addressed in prose, so meaningful gaps remain.

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?

"Launches outreach: real emails and/or LinkedIn invites start in the working window" gives a specific verb (launches), the resource (SDR outreach), and the concrete effect (messages actually go out). It is clearly distinguishable from sdr_preview_launch_outreach and from campaign-launch siblings by naming itself as the SDR-outreach launcher.

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 final sentence establishes an explicit precondition — only call after the user approved sdr_preview_launch_outreach — which routes the agent to the correct sibling first. It also states eligibility conditions (paid plan for managed, connected mailbox for client_owned). It stops short of covering other adjacent siblings such as sdr_pause_outreach / sdr_resume_outreach or what to do if an outreach is already running.

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

All Vendo AI 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?