Skip to main content
Glama
KaiCalls MCP Server

KaiCalls MCP Server

Official

Read agency workspace

get_agency_workspace
Read-onlyIdempotent

Retrieve an agency's assigned installations, support incidents, billing evidence, client activity, and discovery facts to review workspace status and channel readiness.

Instructions

Read assigned installations, grouped support incidents, accepted billing evidence (also billing:read), your clients (line, last 7 days of calls and qualified leads, each client's alert settings, what clients see about you and your own client-activity alerts), or inventory one authorized client's saved facts and actual channel readiness. Suggestions and unknowns remain explicit.

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": {
      "resource": "<resource>",
      "partnerId": "<partnerId>"
    },
    "name": "get_agency_workspace"
  }
}

Input Schema

NameRequiredDescriptionDefault
afterNo
resourceYes
partnerIdYes
businessIdNo

Output Schema

NameRequiredDescriptionDefault
errorNoPresent when success is false
stateNo
successYesWhether the tool completed successfully

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered and the bar is low. The description adds useful scope detail — the 7-day window on client calls and qualified leads, the permission note for billing evidence, and 'grouped' incidents — plus the odd closing claim that 'suggestions and unknowns remain explicit'. It says nothing about pagination, result limits, or authorization failure behavior for a tool that fans out across five resources.

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

Conciseness3/5

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

The lead verb is front-loaded, but the body is a single sprawling sentence with parentheticals nested inside parentheticals ('your clients (line, last 7 days..., each client's alert settings, what clients see...)'), which is hard to parse. The trailing fragment 'Suggestions and unknowns remain explicit' reads as filler rather than information. Information density is high, but structure works against it.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. For a five-resource fan-out tool with two required identifiers, however, the definition leaves the identifier semantics and pagination behavior unexplained. It is adequate to get a call made, but not to make the call correctly on the first try.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry all param meaning and it only partially does. It conveys what each 'resource' value yields, but 'after', 'partnerId' and 'businessId' are never mentioned — an agent gets no signal that 'after' is a pagination cursor or that businessId narrows to a single client. Two of four parameters remain completely opaque.

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 verb 'Read' is paired with an enumeration of what is returned per resource: installations, support incidents, billing evidence, clients, and a per-client fact/channel inventory. That maps onto the five enum values in the schema and lets an agent forecast the payload without opening the schema. It stops short of distinguishing this aggregator from narrower siblings such as get_business_info or get_inbox, and the resource-to-phrase mapping must be inferred because 'discovery' is listed last rather than in enum order.

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

Usage Guidelines2/5

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

There is no statement of when to reach for this tool versus the many single-resource getters in the sibling list, and no exclusions. The only quasi-guidance is the parenthetical '(also billing:read)', which hints at a permission scope rather than usage. Nothing explains when partnerId alone suffices versus when businessId must also be supplied.

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