Skip to main content
Glama

Support: diagnose the workspace and MCP itself

atisbo_support
Read-only

Diagnose Atisbo, including "I connected a source and nothing appeared", "I sent text and no opportunity formed", or "my data is missing". Checks integrations, ingestion, clustering, gates, key scope and migrations, then returns a playbook. share_report files only diagnostics + your text. Use atisbo_lookup/atisbo_analyze for backlog.

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": {
      "problem": "<problem>"
    },
    "name": "atisbo_support"
  }
}

Input Schema

NameRequiredDescriptionDefault
areaNoNarrows the checks. Omit when unsure.
problemYesWhat went wrong, in your words. No customer feedback, docs or credentials — the string IS filed in reports.
share_reportNoFile a verdict-only report when the fault is not caller-side; false = diagnose.
observed_errorNoThe failing error VERBATIM — usually the only evidence.

Output Schema

NameRequiredDescriptionDefault
dataYes
metaYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / area / description
      Previous value: -"Narrows the checks. Omit when unsure — the full set costs the same."New value: +"Narrows the checks. Omit when unsure."
    • changedInput schema / properties / observed_error / description
      Previous value: -"The failing error VERBATIM — diagnostics cannot see the failed call; usually the only evidence."New value: +"The failing error VERBATIM — usually the only evidence."
  2. Changed4 schema fields changed
    • changedInput schema / properties / area / description
      Previous value: -"Narrows which checks run. Omit when unsure — the full set costs the same round-trip."New value: +"Narrows the checks. Omit when unsure — the full set costs the same."
    • changedInput schema / properties / observed_error / description
      Previous value: -"The failing error string VERBATIM — diagnostics cannot see the failed call, so this is often the only evidence."New value: +"The failing error VERBATIM — diagnostics cannot see the failed call; usually the only evidence."
    • changedInput schema / properties / problem / description
      Previous value: -"What went wrong, in your words. Do NOT paste customer feedback, document bodies or credentials — this string IS filed if a report is created."New value: +"What went wrong, in your words. No customer feedback, docs or credentials — the string IS filed in reports."
    • changedInput schema / properties / share_report / description
      Previous value: -"File a verdict-only report when the problem is not caller-side; false = diagnose only."New value: +"File a verdict-only report when the fault is not caller-side; false = diagnose."
  3. Changed1 schema field changed
    • changedOutput schema / properties / data / required
      Previous value: -[
      -  "outcome",
      -  "headline",
      -  "explanation",
      -  "findings",
      -  "next_steps",
      -  "known_issue",
      -  "report_id",
      -  "reported"
      -]New value: +[
      +  "outcome",
      +  "headline",
      +  "explanation",
      +  "findings",
      +  "next_steps",
      +  "reported"
      +]
  4. Changed1 schema field changed
    • changedOutput schema / properties / meta / required
      Previous value: -[
      -  "contract_version",
      -  "tenant_plan",
      -  "workspace_id",
      -  "workspace_name",
      -  "persona",
      -  "scoring_model",
      -  "gates_applied",
      -  "timestamp"
      -]New value: +[
      +  "tenant_plan",
      +  "workspace_id",
      +  "workspace_name",
      +  "timestamp"
      +]
  5. Changed5 schema fields changed
    • removedOutput schema / properties / meta / properties / contract_version / minLength
      Removed value: -1
    • removedOutput schema / properties / meta / properties / persona / minLength
      Removed value: -1
    • removedOutput schema / properties / meta / properties / scoring_model / minLength
      Removed value: -1
    • removedOutput schema / properties / meta / properties / workspace_id / minLength
      Removed value: -1
    • removedOutput schema / properties / meta / properties / workspace_name / minLength
      Removed value: -1
  6. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only cover the safety profile (readOnlyHint=true, destructiveHint=false); the description adds substantive behavior beyond that: the checklist it runs, that it returns a playbook rather than raw data, and crucially the data scope of share_report ("files only diagnostics + your text"). The one caveat is that filing a report is a persistent side effect, which sits in mild tension with readOnlyHint=true — the description is honest about it, but the pairing could confuse an agent about whether anything is written.

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 verb and purpose, then symptoms, then checks, then routing — a logical order with no filler. The three long quoted symptoms consume a lot of the budget for what is essentially example phrasing, but each one maps to a distinct diagnostic area, so little is wasted.

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?

For a multi-subsystem diagnostic tool with an output schema already present, the description covers what is checked, what is returned, how to route elsewhere, and the data-sharing caveat — enough to call it correctly. It does not mention whether diagnosis requires any permissions or how long the checks take, minor gaps given the existing structured data.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description still adds real meaning by clarifying what share_report actually transmits ("only diagnostics + your text"), which the schema's "verdict-only report" phrasing does not make explicit. The `area` enum and `observed_error` semantics are left entirely to the schema.

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 ("Diagnose Atisbo") and grounds it in three concrete symptom scenarios ("connected a source and nothing appeared", "sent text and no opportunity formed", "my data is missing"). It also enumerates the subsystems checked (integrations, ingestion, clustering, gates, key scope, migrations) and what comes back (a playbook), so an agent can distinguish it from the other atisbo_* tools without opening any 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?

Gives clear trigger conditions in the form of quoted user complaints and explicitly routes backlog-shaped work away ("Use atisbo_lookup/atisbo_analyze for backlog"). It lacks an explicit when-not for the remaining siblings (e.g. capture/connect/decide), so the boundary is clear only against two of them.

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.

Resources