Skip to main content
Glama

Start a stack audit (baseline)

start_audit
Read-onlyIdempotent

Start here when the user wants to cut spend across several tools, consolidate apps, or replace one tool safely, and the bills alone won't decide it. Send vendors and team_size (or a stack manifest) and get the few missing facts that would change the answer, ranked by what's at stake, each with where to find it. Fetch those, add them, and call again until status is 'enough', then call next.tool with next.arguments. Send counts, prices, feature and job names only, never raw exports, customer data, secrets or people's names. Stackcut stores the arguments of tool calls to improve its recommendations (vendor names, prices, seats, features, usage numbers, billing amounts and project descriptions; account keys only as a one-way hash, billing and validation sources not at all; never IP addresses). Tool results are summarized; exit tools log only result counts, qualification flags and public evidence statuses, not answer contents. Don't send personal data or secrets.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalNodecision in words, e.g. 'cut costs'
vendorsNoNames (['Notion', 'Asana']) or service objects.
decisionNoWith vendors: what the audit is for (default cut_spend).
manifestNoA stack manifest (JSON Schema at https://stackcut.io/schemas/stack-manifest-1.json; manifest_version '1'): goal, org, builder, services (vendor, plan, monthly_spend_usd, seats, active_users, features_used, usage, renewal_date, …), workflows, unknowns.
team_sizeNoWith vendors: people on the team.
max_questionsNoMost questions to return (default 8).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / vendors / description
      Previous value: -"A first pass: names (['Notion', 'Asana']) or service objects ({vendor, plan, monthly_spend_usd, seats})."New value: +"Names (['Notion', 'Asana']) or service objects."
    • changedInput schema / properties / vendors / items / anyOf
      Previous value: -[
      -  {
      -    "maxLength": 200,
      -    "minLength": 1,
      -    "type": "string"
      -  },
      -  {
      -    "required": [
      -      "vendor"
      -    ],
      -    "type": "object"
      -  }
      -]New value: +[
      +  {
      +    "maxLength": 200,
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  {
      +    "properties": {
      +      "monthly_spend_usd": {
      +        "type": "number"
      +      },
      +      "plan": {
      +        "type": "string"
      +      },
      +      "seats": {
      +        "type": "integer"
      +      },
      +      "vendor": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "vendor"
      +    ],
      +    "type": "object"
      +  }
      +]
  2. Changed6 schema fields changed
    • addedInput schema / properties / goal
      Added value: +{
      +  "description": "decision in words, e.g. 'cut costs'",
      +  "maxLength": 200,
      +  "type": "string"
      +}
    • changedInput schema / properties / vendors / description
      Previous value: -"A first pass without a manifest: the tools the team pays for, e.g. ['Notion', 'Asana', 'Loom']."New value: +"A first pass: names (['Notion', 'Asana']) or service objects ({vendor, plan, monthly_spend_usd, seats})."
    • addedInput schema / properties / vendors / items / anyOf
      Added value: +[
      +  {
      +    "maxLength": 200,
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  {
      +    "required": [
      +      "vendor"
      +    ],
      +    "type": "object"
      +  }
      +]
    • removedInput schema / properties / vendors / items / maxLength
      Removed value: -200
    • removedInput schema / properties / vendors / items / minLength
      Removed value: -1
    • removedInput schema / properties / vendors / items / type
      Removed value: -"string"
  3. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the description is free to add what they can't: the iterative question-answer loop, the next.tool/next.arguments chaining contract, the 'status is enough' termination condition, and a detailed data-retention disclosure of what arguments are stored and what is excluded. That is substantive behavior beyond structured fields.

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 trigger and the loop protocol are front-loaded, which is good. But roughly half the text is dense privacy/retention boilerplate, and the closing sentence 'Don't send personal data or secrets' restates the earlier prohibition, so the description is longer than it needs to be.

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?

With no output schema, the description carries the burden of explaining returns and largely does: it describes the ranked questions with sources, the status field, and the next.tool/next.arguments handoff. For a 6-parameter, nested-object entry-point tool with a 100%-covered schema, the remaining gap is only the full response shape, which is minor.

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 the schema already documents goal, vendors, decision, manifest, team_size, and max_questions. The description reinforces the two main input shapes (vendors + team_size, or a stack manifest) and adds a content constraint ('counts, prices, feature and job names only'), but adds no format or semantics beyond what the schema provides.

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 description states a specific action (start an audit) and a specific output (the few missing facts ranked by what's at stake, each with where to find it), plus the entry-point framing 'Start here when...'. It never names or contrasts the sibling tools audit_stack, choose_stack, or plan_stack_from_spec, so an agent cannot fully disambiguate from the description alone.

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?

Trigger conditions are explicit and concrete: 'cut spend across several tools, consolidate apps, or replace one tool safely, and the bills alone won't decide it.' The follow-up protocol is also spelled out ('add them, and call again until status is enough, then call next.tool with next.arguments'), which is unusually actionable. It stops short of stating when to prefer a sibling instead.

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.