Frasma

Prepare diagnostic summary handoff

prepare_diagnostic_summary

Read-onlyIdempotent

Validates a complete diagnostic summary and returns a handoff payload. Does not send email. Map the diagnosis to a process brief; the user must confirm before POST /api/request-process-assessment.

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": {
      "clientName": "<clientName>",
      "clientEmail": "<clientEmail>",
      "sector": "<sector>",
      "process": "<process>",
      "currentWorkflow": "<currentWorkflow>",
      "bottlenecks": "<bottlenecks>",
      "currentSystems": "<currentSystems>",
      "volumesAndFrequency": "<volumesAndFrequency>",
      "baselineMetrics": "<baselineMetrics>",
      "dataAvailable": "<dataAvailable>",
      "constraints": "<constraints>",
      "desiredOutcomes": "<desiredOutcomes>",
      "needCategories": "<needCategories>",
      "opportunities": "<opportunities>",
      "recommendations": "<recommendations>",
      "openQuestions": "<openQuestions>",
      "nextSteps": "<nextSteps>",
      "language": "<language>"
    },
    "name": "prepare_diagnostic_summary"
  }
}

Input Schema

Name	Required	Description
`sector`	Yes	Business sector, e.g. manufacturing or food quality.
`process`	Yes	Short name of the process under diagnosis, e.g. delivery notes into ERP.
`honeypot`	No	Anti-spam trap. Must be empty or omitted.
`language`	Yes	Language of the diagnostic summary: it or en.
`nextSteps`	Yes	Agreed next steps after reviewing this summary.
`clientName`	Yes	Client full name.
`bottlenecks`	Yes	Observed bottlenecks, one item per string.
`clientEmail`	Yes	Client work email.
`constraints`	Yes	Hard constraints, e.g. human validation before ERP import.
`clientCompany`	No	Client company name, if known.
`dataAvailable`	Yes	Data that can be shared for a prototype, preferably anonymized samples.
`openQuestions`	Yes	Open questions still to confirm with the client.
`opportunities`	Yes	Concrete opportunities that follow from the evidence.
`currentSystems`	Yes	Systems already in use, e.g. email, PDF, Mago Zucchetti.
`needCategories`	Yes	One or more Frasma need categories that fit the diagnosis.
`baselineMetrics`	Yes	Baseline metrics before any Frasma work, e.g. minutes per document.
`currentWorkflow`	Yes	How the process is done today, including people, tools, and handoffs.
`desiredOutcomes`	Yes	Desired outcomes without invented savings or guarantees.
`recommendations`	Yes	Recommended next steps for a limited prototype or discovery.
`volumesAndFrequency`	Yes	Volumes and frequency, e.g. about 40 DDT per day.

Output Schema

Name	Required	Description	Default
`ok`	Yes
`handoff`	Yes
`summary`	Yes
`completeness`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 1, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already mark the tool as read-only, idempotent, and non-destructive, so the description does not need to repeat that. It adds value by disclosing that no email is sent and that the actual POST is deferred until user confirmation, clarifying side-effect boundaries beyond the annotations.

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?

Three short sentences with the main action first, a side-effect disclaimer second, and workflow guidance third. There is no redundant restating of schema or annotations.

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 20-parameter tool, the description gives the essential orchestration context: it validates a summary, returns a payload, sends nothing, and is a prerequisite to a user-confirmed POST; the output schema and parameter schema cover the remaining details. The ambiguous 'process brief' mapping and lack of validation-criteria detail keep it from a 5.

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%, so parameters are already fully documented with rich descriptions, giving a baseline of 3. The tool description adds no additional parameter-level semantics; the only adjacent hint, 'Map the diagnosis to a process brief,' is too vague to clarify any specific argument.

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 first sentence states a concrete action: validates a complete diagnostic summary and returns a handoff payload, and 'Does not send email' narrows the scope. However, it does not clearly distinguish itself from the prepare_project_brief sibling, and the instruction 'Map the diagnosis to a process brief' blurs the tool's exact role.

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 useful when-to-use context: this is a validation/handoff step, not an email or submission action, and it must precede POST /api/request-process-assessment only after user confirmation. It does not explicitly name alternatives or state when to prefer prepare_project_brief, so the guidance is clear but not exhaustive.

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

All Frasma 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.