Skip to main content
Glama

suggest_actions

Produce prioritized follow-up actions for an analyzed call—manager alerts for churn threats, customer callbacks, CRM tickets—each with a reason and triggering sentence. Sends nothing.

Instructions

Suggest follow-up actions for an analyzed call: manager alert (churn threat or complaint), customer callback (to check an agent promise is kept), CRM ticket (negative sentiment). Each action has a priority, a reason and the sentence that triggered it. Sends nothing.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "call_id": "<call_id>"
    },
    "name": "suggest_actions"
  }
}

Input Schema

NameRequiredDescriptionDefault
call_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
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 "Sends nothing" is the crucial disclosure that no alerts, callbacks, or tickets are actually created — the tool is advisory only. The response shape (priority, reason, triggering sentence) is also described. It does not state prerequisites such as whether the call must already have been analyzed, or what happens for an unanalyzed call_id.

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?

Three tight sentences: purpose first, the action-type mapping second, and the no-side-effect guarantee last. Every clause carries information; nothing is repeated or padded.

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?

For a single-parameter, no-output-schema tool with no annotations, the definition covers purpose, triggering rules, return contents, and side-effect posture. The main remaining gap is the prerequisite relationship to the analysis step and error behavior for a call that has not been analyzed.

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?

There is one required parameter (call_id) with zero schema description coverage, so the description must compensate. "For an analyzed call" implies the parameter identifies a previously analyzed call, which is weak but useful inference; the description never names or clarifies the parameter, its format, or whether only analyzed calls are valid.

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 ("suggest follow-up actions for an analyzed call") and enumerates the concrete action types produced. The phrase "for an analyzed call" distinguishes it from analyze_call and get_call_insights, which produce the analysis rather than follow-ups.

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 context for use (an already-analyzed call) and maps trigger conditions to each action type: churn threat or complaint to manager alert, agent promise to callback, negative sentiment to CRM ticket. It does not explicitly name sibling tools or state when to prefer them, so no exclusions are offered.

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