Skip to main content
Glama
KaiCalls MCP Server

KaiCalls MCP Server

Official

Teach Coaching Rule

teach_coaching_rule
Idempotent

Adds a coaching rule from a call to the agent's versioned, rollback-ready instructions, then runs a test built from that call to confirm the agent follows it.

Instructions

Teach the agent one rule from a coaching point on a call (get_coaching gives the code and a suggested rule). The rule is added to a Coaching rules section of the agent's instructions through the governed update path, so it is versioned, in change history and can be rolled back; a business owner or admin signed in through this connector applies it right away, otherwise it waits for the owner. Then a test is built from that call and run, and the result says whether the agent now follows the rule.

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>",
      "code": "<code>",
      "rule": "<rule>"
    },
    "name": "teach_coaching_rule"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeYesThe coaching point code from get_coaching.
ruleYesOne plain instruction the agent should follow on every call (8-300 characters). Usually the suggested rule from get_coaching.
call_idYesThe call the coaching point is on.
business_idNoBusiness ID. Required when the key can reach more than one business.

Output Schema

NameRequiredDescriptionDefault
ruleNo
testNo
errorNoPresent when success is false
statusNo
successYesWhether the tool completed successfully

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only say this is a non-read, idempotent, non-destructive mutation. The description goes well beyond: the rule lands in a versioned Coaching rules section via a governed update path, is captured in change history, is rollback-able, and application timing depends on caller role (immediate for owner/admin, queued otherwise). It also discloses the follow-on side effect of building and running a test and reporting whether the agent now complies.

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?

Purpose and provenance are front-loaded in the first sentence, followed by governance/permission effects and the resulting test. Each sentence carries distinct information, though the middle sentence is dense and could be split for readability.

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

Completeness5/5

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

For a mutation tool with an output schema and full annotation coverage, the description supplies everything an agent needs: required inputs and their source, permission-dependent behavior, versioning/rollback implications, and the fact that a verification test is run and reported.

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 100%, so the schema already explains every parameter, including that code comes from get_coaching and rule is the plain instruction. The description reinforces the code/rule provenance but adds little semantic detail the schema does not already carry, so this sits at the baseline.

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: teaching one rule derived from a coaching point on a call. It names the originating sibling (get_coaching) that supplies the code, so an agent can distinguish this write tool from the read tool that surfaces coaching points.

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 description establishes the prerequisite workflow clearly: get_coaching supplies the code and a suggested rule, and this tool applies it. It also distinguishes the immediate-apply case (business owner or admin signed in) from the pending case. It stops short of stating explicit when-not-to-use conditions, so it lands just below the top.

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

Deploy Server

Other Tools