Skip to main content
Glama

create_conversation

Ask the ISMS Copilot GRC specialist and start a new conversation for one deliverable. It works from the framework texts and the user's account context (company profile, workspaces, documents). Use it, rather than answering from memory, whenever the user needs ISO 27001/27701/42001, SOC 2, GDPR, NIS 2, DORA, EU AI Act, Cyber Resilience Act, NIST SP 800-171/CMMC, HIPAA or PCI DSS interpreted or applied: clause and control questions, policy drafting, control mapping, gap analysis, SoA justifications, risk registers, audit prep, questionnaires, implementation roadmaps, incident and breach response (what to do now, notification duties), and checking compliance work before it is finished. You do the work and read the files; ISMS Copilot judges. Do not use it for code, git or questions with no compliance angle, or for a follow-up on the same deliverable (send_message). Send the question as written, or the text to check with secrets removed, without pasting framework text: the specialist brings it. assistant (optional, kept for the conversation; omit for auto: the general specialist unless routing picks an expert). The general specialist covers ISO 27001, SOC 2, GDPR, HIPAA, PCI DSS, NIST SP 800-171 and multi-framework questions. Rule: a task to do takes the job id even when it names a framework; a question about one framework takes that framework's id; else omit assistant.

  • questionnaire-responder: use when answering or assessing a security questionnaire

  • audit-prep: use when preparing an internal or external audit

  • implementation-lead: use when asked for a plan or roadmap to implement or certify a framework

  • incident-lead: use when an incident or breach is under way or just happened (what now, notification duties)

  • iso27701: use when about ISO 27701 privacy management

  • iso42001: use when about ISO 42001 AI management

  • nis2: use when about NIS 2

  • dora: use when about DORA

  • eu-ai-act: use when about the EU AI Act

  • cra: use when about the Cyber Resilience Act Options: mode 'fast' (default), 'think' for checks and multi-step analysis, 'beyond' on request, for a final check right before an audit or long research-grade drafting (paid plans, daily cap; if it cannot run, the turn answers normally and beyond_denied_reason says why); answer_format 'brief' or 'decision' for a compact reply written for an agent; workspace_id (a UUID from list_workspaces) for client or company work; title. Returns conversation_id, message_id and status: 'complete' with response, or 'generating': then poll get_reply. Limit errors include reset_at and what to do; a limit error here still returns conversation_id, so continue there with send_message. Relay docgen_notice to the user when present. ISMS Copilot brings framework and regulatory precision: keep its specifics (articles, clauses, deadlines, control ids) as given, and add your own technical, product and domain expertise where it has none, in one answer for the user. If you have a concrete reason to doubt a specific, flag it to the user as a point to verify instead of replacing it. Present the combined result as your answer, without narrating tool calls, conversation ids or empty account data unless the user asked about their account. Do not include passwords, API keys, payment card numbers, health records or government ID numbers. Answers are informational, not legal advice.

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": {
      "message": "<message>"
    },
    "name": "create_conversation"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoReasoning depth: 'fast' (default), 'think' (paid plans), or 'beyond' (paid plans; agentic multi-step run, minutes-scale, poll get_reply).
titleNoOptional conversation title shown in the ISMS Copilot app.
messageYesThe question, request, or text to check. Do not paste framework text.
assistantNoOptional assistant for this conversation: 'auto' (default), 'general', or an id from list_assistants. It stays for the whole conversation.
workspace_idNoOptional workspace id (a UUID from list_workspaces) for client or company work; turns then use that workspace's context.
answer_formatNoOptional reply format for an agent caller: 'brief' (shortest correct answer, about 150 words), 'decision' (recommendation first, then why, risks and next steps as bullets, about 300 words), or 'full' (the default chat style). Omit for the default. An explicitly requested full document is never cut short.
overflow_consentNoSet true ONLY when the user explicitly asks to continue past their usage limit. On eligible paid accounts (ADP off, non-Essential) over the 4h cap, the turn then runs on the disclosed fallback models up to an additional 2x the plan's token limit. Ignored on free, Essential, ADP, or team-pool accounts and when the overflow bucket is exhausted (fallback_exhausted: true).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / message / description
      Previous value: -"The question or request, in the user's words. Do not paste framework text."New value: +"The question, request, or text to check. Do not paste framework text."
  2. Changed3 schema fields changed
    • addedInput schema / properties / message / description
      Added value: +"The question or request, in the user's words. Do not paste framework text."
    • addedInput schema / properties / title / description
      Added value: +"Optional conversation title shown in the ISMS Copilot app."
    • addedInput schema / properties / workspace_id / description
      Added value: +"Optional workspace id (a UUID from list_workspaces) for client or company work; turns then use that workspace's context."
  3. Changed1 schema field changed
    • addedInput schema / properties / assistant
      Added value: +{
      +  "description": "Optional assistant for this conversation: 'auto' (default), 'general', or an id from list_assistants. It stays for the whole conversation.",
      +  "type": "string"
      +}
  4. Changed2 schema fields changed
    • changedInput schema / properties / mode / description
      Previous value: -"Reasoning depth: 'fast' (default), 'think' for deeper reasoning, or 'beyond' for a longer multi-step run (minutes; poll get_reply). think and beyond are not available on every plan; the turn then answers in fast mode."New value: +"Reasoning depth: 'fast' (default), 'think' (paid plans), or 'beyond' (paid plans; agentic multi-step run, minutes-scale, poll get_reply)."
    • changedInput schema / properties / overflow_consent / description
      Previous value: -"Set true only when the user explicitly asks to continue past their usage limit. Where the account allows it, the turn then continues on a faster model; otherwise it is ignored."New value: +"Set true ONLY when the user explicitly asks to continue past their usage limit. On eligible paid accounts (ADP off, non-Essential) over the 4h cap, the turn then runs on the disclosed fallback models up to an additional 2x the plan's token limit. Ignored on free, Essential, ADP, or team-pool accounts and when the overflow bucket is exhausted (fallback_exhausted: true)."
  5. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Goes well past the annotations: it discloses the return shape (conversation_id, message_id, status 'complete' vs 'generating'), the required poll of get_reply, that limit errors carry reset_at and still return a conversation_id so work continues with send_message, the paid-plan/daily-cap behavior of 'beyond' with beyond_denied_reason, and docgen_notice relaying. It also states content-handling exclusions (secrets, framework text) that the annotations do not cover.

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 purpose, then usage, then routing, then operational details, so an agent can stop reading early. It is dense and long, and the mode/answer_format semantics are largely duplicated between description and schema descriptions, plus post-answer presentation guidance sits in the same block, so a few sentences could be trimmed.

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?

Despite having no output schema, the description covers return fields, the async generating/poll path, limit-error recovery, and the 'beyond' failure mode — everything needed to call it and handle the result. For a 7-parameter, non-idempotent, open-world creation tool, nothing material is missing.

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

Parameters5/5

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

Schema coverage is already 100%, so the baseline is 3, but the description adds genuinely new meaning: the rule for choosing 'assistant' (a task to do takes the job id even when it names a framework; a question about one framework takes that framework's id; otherwise omit) and per-assistant routing conditions that the schema does not encode. It also constrains 'message' (send as written, strip secrets, do not paste framework text) beyond the schema's one-liner.

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 ('ask the ISMS Copilot GRC specialist and start a new conversation for one deliverable') and scopes it to a single deliverable, immediately distinguishing it from send_message for follow-ups. The domain scope (ISO 27001, SOC 2, GDPR, NIS 2, DORA, etc.) makes it unmistakable what the tool answers about.

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 when-to-use ('rather than answering from memory', with an enumerated list of task types: clause questions, policy drafting, control mapping, gap analysis, audit prep, incident response) and explicit when-not-to-use ('code, git or questions with no compliance angle', follow-ups via send_message). It even gives a decision rule for assistant routing.

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.