Skip to main content
Glama

Switch Active Company

switch_active_company

Point the formation tools at a different company the customer already owns. Use when the customer asks to manage / continue / inspect a specific company by name or ID. The companyId must come from list_companies — unknown IDs are rejected. After switching, the response carries the same shape as get_company_onboarding_status for the new active company, so the agent knows immediately which step to resume from. The override is process-local; if the customer reconnects and ends up on a different MCP replica, just call this tool again.

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": {
      "companyId": "<companyId>"
    },
    "name": "switch_active_company"
  }
}

Input Schema

NameRequiredDescriptionDefault
contextNoOptional, for analytics only. In one sentence, why you are calling this tool and how it serves the user's goal. Describe the purpose in general terms: never include names, emails, phone numbers, addresses, IDs or any other personal details.
companyIdYesTarget companyId — must be one of the IDs returned by list_companies for this customer.
llm_modelNoOptional, for analytics only. Your exact model identifier from your system prompt (e.g. "claude-opus-4-8"), or "unknown" if unsure. Never guess.
conversation_idNoOptional, for analytics only. The exact conversation_id from this server's previous response, unchanged. The first response provides one, so leave this out until you have it and never invent one. Keep passing the same value for the rest of the conversation, even when the user moves on to a new request.

Output Schema

NameRequiredDescriptionDefault
emailNoCustomer email
errorNotrue if an error occurred
messageNoHuman-readable status
blockersNoPrerequisites still unmet, in flow order. Same vocabulary as the `missing` array submit_for_review returns. Empty array when formation is fully complete.
lastNameNoCustomer last name
nextStepNoThe step the formation flow now waits on; null once formation is complete.
companyIdNoCustomer's active formation company ID, if any
firstNameNoCustomer first name
customerIdNoCustomer ID from the OAuth bearer
dashboardUrlNoURL to doola dashboard
nextQuestionNoThe customer-facing question for nextStep; null once formation is complete.
completedStepsNoList of steps inferred as completed from the Company / Customer state
conversation_idNoThis conversation's handle. Pass it unchanged as conversation_id on every later call.
hasActiveSessionNofalse if the request was not authenticated (defense in depth)
suggestedNextStepNoThe tool for the step the flow waits on, as in nextStep; null when formation is complete.
countryOfResidenceNoISO Alpha-3 country code if set
responsiblePartySsnOnFileNoWhether doola has the responsible party's SSN for the EIN application. Only ever this boolean: no tool returns the SSN or any part of it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedOutput schema / properties / message / description
      Previous value: -"Human-readable status or instruction"New value: +"Human-readable status"
    • removedOutput schema / properties / nextAction
      Removed value: -{
      -  "description": "Imperative for the agent — follow verbatim. Null when formation is complete.",
      -  "type": [
      -    "string",
      -    "null"
      -  ]
      -}
    • removedOutput schema / properties / nextActionInput
      Removed value: -{
      -  "description": "{tool, arguments} template for the resume point's call. Replace every <placeholder> in arguments with the user's real answer. Null when formation is complete.",
      -  "type": [
      -    "object",
      -    "null"
      -  ]
      -}
    • changedOutput schema / properties / nextQuestion / description
      Previous value: -"Question to ask the user verbatim before the next formation call. Null when no question is needed."New value: +"The customer-facing question for nextStep; null once formation is complete."
    • addedOutput schema / properties / nextStep
      Added value: +{
      +  "description": "The step the formation flow now waits on; null once formation is complete.",
      +  "properties": {
      +    "description": {
      +      "description": "Where the customer stands at this step and what their options are.",
      +      "type": "string"
      +    },
      +    "missingFields": {
      +      "description": "Arguments of that tool the step still needs.",
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "tool": {
      +      "description": "The tool that records this step.",
      +      "type": "string"
      +    }
      +  },
      +  "type": [
      +    "object",
      +    "null"
      +  ]
      +}
    • changedOutput schema / properties / suggestedNextStep / description
      Previous value: -"The next formation step to call; null when formation is complete."New value: +"The tool for the step the flow waits on, as in nextStep; null when formation is complete."
  2. Changed1 schema field changed
    • addedOutput schema / properties / responsiblePartySsnOnFile
      Added value: +{
      +  "description": "Whether doola has the responsible party's SSN for the EIN application. Only ever this boolean: no tool returns the SSN or any part of it.",
      +  "type": "boolean"
      +}
  3. Changed2 schema fields changed
    • addedInput schema / properties / conversation_id
      Added value: +{
      +  "description": "Optional, for analytics only. The exact conversation_id from this server's previous response, unchanged. The first response provides one, so leave this out until you have it and never invent one. Keep passing the same value for the rest of the conversation, even when the user moves on to a new request.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / conversation_id
      Added value: +{
      +  "description": "This conversation's handle. Pass it unchanged as conversation_id on every later call.",
      +  "type": "string"
      +}
  4. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare it is not read-only and not destructive, and the description explains why: it mutates a process-local active-company pointer that redirects subsequent formation tools. It goes further than the annotations by disclosing the rejection behavior for unknown IDs, the response shape equivalence with get_company_onboarding_status, and the important caveat that the override is process-local and may need re-invocation on a different MCP replica — non-obvious state semantics an agent could not infer otherwise.

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?

Four sentences, each carrying distinct information: purpose, trigger, precondition, post-call result, and the replica caveat. The action is front-loaded in the first sentence, and there is no restatement of the schema or filler.

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?

The tool has an output schema, so return values need not be enumerated, and the description instead usefully cross-references that the response mirrors get_company_onboarding_status so the agent knows which step to resume. Combined with the state-scope caveat and ID precondition, nothing material is missing for a one-required-parameter switching tool.

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% and the schema already states that companyId must be one of the IDs returned by list_companies, so the description's restatement of that constraint adds little. The one genuine addition is that unknown IDs are rejected rather than ignored, but the description adds nothing about the analytics-only parameters (context, llm_model, conversation_id), leaving the baseline 3 appropriate.

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?

The opening sentence names the exact verb and resource — 'Point the formation tools at a different company' — and scopes it to companies the customer already owns, which separates it from start_new_company and start_formation. It also distinguishes the resource provenance (companyId from list_companies), so an agent can tell it apart from all twelve siblings without opening a schema.

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?

It gives an explicit trigger — 'when the customer asks to manage / continue / inspect a specific company by name or ID' — plus a hard precondition that the ID must originate from list_companies and that unknown IDs are rejected. It also covers the reconnect/replica case with a concrete instruction. What is missing is an explicit statement of when NOT to use it (e.g., single-company customers who never need a switch), so it falls just short of the top band.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.