KaiCalls

Customize Business Line

set_up_business

Idempotent

Optional line customization: use only when the owner explicitly asks Kai to answer with a business name and greeting. Never required to make calls, and never changes payment, usage or fraud limits. Extra business details are optional; do not ask a business-qualification questionnaire. An existing business greeting is left unchanged.

Input Schema

Name	Required	Description
`website`	No	The business's website, if it has one.
`business_id`	No	The account to set up. Optional when the token reaches one account.
`business_name`	Yes	The business's real name.
`what_you_sell`	No	What the business sells or does, in the owner's words.
`who_kai_will_call`	No	Who the owner wants Kai to call, e.g. other businesses, existing customers, or people who asked for a callback.

Output Schema

Name	Required	Description
`error`	No	Present when success is false
`changed`	No
`success`	Yes	Whether the tool completed successfully
`business_id`	No
`persona_mode`	No
`already_business`	No
`greeting_updated`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 11, 2026

changedInput schema / required

Previous value: -[
-  "business_name",
-  "what_you_sell",
-  "who_kai_will_call"
-]New value: +[
+  "business_name"
+]

AddedOct 11, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare non-read-only but non-destructive and idempotent. The description adds real scope boundaries beyond that: it does not change payment, usage or fraud limits, and an existing business greeting is left unchanged. It stops short of stating auth or return behavior.

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?

Front-loaded with the primary condition, then the negative constraints. Four sentences all carry weight, though the phrasing is slightly repetitive around optionality.

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?

An output schema exists, and annotations plus full schema coverage carry structural detail, so the description only needed usage and scope boundaries — which it supplies. Nothing critical for correct invocation is missing.

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 100%, so every parameter is already documented, including the required business_name and optional business_id/website. The description only adds that extra details are optional and should not be solicited, which is mild guidance rather than new parameter semantics. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening states the operation concretely: customizing how Kai answers with a business name and greeting. It is distinguishable from siblings like get_business_info (read) and configure_agent_business_rules (rules), though the verb 'set_up' is softened by 'optional line customization' rather than a crisp verb+resource.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit gating: use only when the owner explicitly asks for a business name and greeting; never required to make calls; do not run a qualification questionnaire. It names the condition to act and two conditions not to act, leaving little to inference.

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

All KaiCalls 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.