crm_reply_to_leadSends a REAL LinkedIn message or email reply to the lead on their source channel, from the customer's own account. Also moves the lead to the "Manager Dialog" stage. ALWAYS show the drafted text to the human and get approval BEFORE calling this.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| text | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / channelRemoved value: -{
- "enum": [
- "email",
- "linkedin"
- ],
- "type": "string"
-}Input schema / properties / subjectRemoved value: -{
- "type": "string"
-}Input schema / properties / channelAdded value: +{
+ "enum": [
+ "email",
+ "linkedin"
+ ],
+ "type": "string"
+}Input schema / properties / subjectAdded value: +{
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does so well: it flags that a real external message is sent from the customer's own account (irreversible external side effect), discloses a state change (lead moved to 'Manager Dialog' stage), and imposes a human-approval gate. These are exactly the behavioral facts an agent needs before mutating state.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no waste, and the highest-stakes information (this sends a real outbound message) is front-loaded, with the approval warning last. Every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description covers the external side effect, the internal state change, and the approval prerequisite. It omits failure/error behavior and whether repeated calls resend the message, which would fully close the loop.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Two required parameters with 0% schema description coverage, so the description must compensate. It implies the 'text' parameter ('the drafted text') but says nothing about the 'id' parameter's expected format or source, leaving half the parameters undocumented. It adds marginal but incomplete meaning beyond the bare schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (sends/reply), resource (LinkedIn message or email reply to a lead), and scope (their source channel, from the customer's own account). The explicit 'REAL outbound message' framing distinguishes it from read-only or note-adding siblings like crm_add_comment and crm_get_conversation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives an explicit prescriptive precondition: 'ALWAYS show the drafted text to the human and get approval BEFORE calling this.' That is strong when-to-use guidance. It stops short of naming alternative tools (e.g., crm_add_comment for non-outbound notes) or when-not-to-use cases, so it is clear context without exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.