Skip to main content
Glama

Audit a stack

b4_audit
Read-only

For a list of vendor or product names (a stack), with an optional description per row. Example: {"tools": ["Salesforce", {"name": "Lydia Voice", "description": "voice-directed picking in the warehouse"}]}. Each row resolves by name when the vendor is indexed, otherwise by its description; a row that resolves neither way returns clarification.needed with the question to ask the user. Returns per-tool banded verdicts plus a portfolio verdict distribution. Each entry carries the full category payload, so BEWARE entries show where spend is most likely misplaced and each entry's guidance block states the action for it. Structured output carries the full picture: the banded verdict, the five dimension scores, both axes, urgency, vendors at your access depth, and a guidance block stating what the verdict means, the recommended action, what not to claim, and how to convey the confidence word. Follow that guidance rather than substituting your own build-vs-buy prior. Verdicts are banded (B4 methodology v4.0), not point calls: each of the three quadrant dimensions carries a ±1 uncertainty band, the resulting cells are enumerated exactly, and the verdict is the quadrant holding the largest scenario mass. Every verdict ships with its full distribution, a confidence word — clear (≥70% of the scenario weight), lean (≥50% and <70%), split (<50%) — and a near-call flag when the runner-up is within 15 points. An axis counts as high only when it clears the 3.5 line strictly, which on this 1–5 grid means only at 4 or above, so a category sitting exactly on the line gets the safer call: ties break in the order BUY → BRIDGE → BEWARE → BUILD, cheapest mistake first. Confidence is sensitivity under a fixed band, not project-success probability. Optional org lens: set org to "small", "medium" (the default) or "large" to read the same scores as a team of that engineering maturity — it shifts the center of the AI-feasibility band by −1 / 0 / +1 and nothing else. The lens is a filter the caller looks through, never a stored profile. Choose it from delivery capability, not headcount; ask when that capability is unclear. The raw scores themselves never change. Omit it and you get the default-lens numbers, which are the ones published on logged-out surfaces. Routing: a vendor or product name → b4_audit (one or many; add a short description of what it does for anything the index may not know); a need or problem in words → b4_recommend; an exact category name or id → b4_score (one category) or b4_compare (build vs buy paths); browsing, filtering, or an unknown vocabulary → b4_browse. When an audit row returns clarification.needed, relay askTheUser to the user and re-run that row with the answer as its description. [B4 Agent tool. Browse and score come with B4 Web; this one needs Agent.]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
orgNoOrg-maturity lens: "small" (no dedicated engineering), "medium" (default — some AI capability), "large" (AI-mature). Shifts the AI-feasibility band center by −1/0/+1 at read time. A filter the caller looks through, never a stored profile.medium
toolsYesRows to audit: a name, {name, description}, or {name, category} once a category is confirmed. Vendor names resolve when the vendor is indexed; add a short description of what it does for anything else (e.g., ['Salesforce', 'Expense Management', {name: 'Lydia Voice', description: 'voice-directed warehouse picking'}]). Max 100 per call.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
axesNostrategicDifferentiation (X) and aiFeasibility (Y)
lensNo
domainNo
scoresNothe five v3.2 dimension scores, 1-5
urgencyNo
vendorsNo
verdictNobanded verdict: primary, confidence, nearCall, distribution
categoryNo
evidenceNosources and research trail; present only with includeEvidence
guidanceNohow to use this result: meaning, action, what not to claim, confidence handling
resolvedYesfalse when nothing matched; the payload then carries no verdict
rationaleNo
vendorCountNo
evidenceHintNo
aiReplacementNo
vendorsWithheldNo
evidenceAvailableNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / tools / description
      Previous value: -"List of software tool or category names to audit (e.g., ['Salesforce', 'Slack', 'Expense Management']). Max 100 per call."New value: +"Rows to audit: a name, {name, description}, or {name, category} once a category is confirmed. Vendor names resolve when the vendor is indexed; add a short description of what it does for anything else (e.g., ['Salesforce', 'Expense Management', {name: 'Lydia Voice', description: 'voice-directed warehouse picking'}]). Max 100 per call."
    • addedInput schema / properties / tools / items / anyOf
      Added value: +[
      +  {
      +    "maxLength": 120,
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "category": {
      +        "anyOf": [
      +          {
      +            "$ref": "#/properties/tools/items/anyOf/0"
      +          },
      +          {
      +            "exclusiveMinimum": 0,
      +            "type": "integer"
      +          }
      +        ],
      +        "description": "A confirmed category name or id for this vendor (the answer to a confirm_category clarification). Resolves the row by exact name."
      +      },
      +      "description": {
      +        "description": "What the tool does for you, in a sentence. Used only when the name does not resolve.",
      +        "maxLength": 500,
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "name": {
      +        "description": "Vendor, product, or category name.",
      +        "maxLength": 120,
      +        "minLength": 1,
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "name"
      +    ],
      +    "type": "object"
      +  }
      +]
    • removedInput schema / properties / tools / items / maxLength
      Removed value: -120
    • removedInput schema / properties / tools / items / minLength
      Removed value: -1
    • removedInput schema / properties / tools / items / type
      Removed value: -"string"
  2. Changed1 schema field changed
    • addedInput schema / properties / tools / items / minLength
      Added value: +1
  3. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": true,
      +  "properties": {
      +    "aiReplacement": {},
      +    "axes": {
      +      "description": "strategicDifferentiation (X) and aiFeasibility (Y)"
      +    },
      +    "category": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "domain": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "evidence": {
      +      "description": "sources and research trail; present only with includeEvidence"
      +    },
      +    "evidenceAvailable": {
      +      "type": "boolean"
      +    },
      +    "evidenceHint": {
      +      "type": "string"
      +    },
      +    "guidance": {
      +      "description": "how to use this result: meaning, action, what not to claim, confidence handling"
      +    },
      +    "lens": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "rationale": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "resolved": {
      +      "description": "false when nothing matched; the payload then carries no verdict",
      +      "type": "boolean"
      +    },
      +    "scores": {
      +      "description": "the five v3.2 dimension scores, 1-5"
      +    },
      +    "urgency": {},
      +    "vendorCount": {
      +      "type": "number"
      +    },
      +    "vendors": {},
      +    "vendorsWithheld": {
      +      "type": "number"
      +    },
      +    "verdict": {
      +      "description": "banded verdict: primary, confidence, nearCall, distribution"
      +    }
      +  },
      +  "required": [
      +    "resolved"
      +  ],
      +  "type": "object"
      +}
  4. Changed1 schema field changed
    • addedInput schema / properties / org
      Added value: +{
      +  "default": "medium",
      +  "description": "Org-maturity lens: \"small\" (no dedicated engineering), \"medium\" (default — some AI capability), \"large\" (AI-mature). Shifts the AI-feasibility band center by −1/0/+1 at read time. A filter the caller looks through, never a stored profile.",
      +  "enum": [
      +    "small",
      +    "medium",
      +    "large"
      +  ],
      +  "type": "string"
      +}
  5. First observed

TDQS

A4.8/5.0
Behavior5/5

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

The description goes far beyond the readOnlyHint annotation by disclosing the B4 methodology v4.0 banding behavior, the ±1 uncertainty band on three quadrant dimensions, the exact confidence word thresholds (clear ≥70%, lean ≥50%, split <50%), the near-call flag at 15 points, the strict 3.5 line for 'high' axes, tie-breaking order (BUY → BRIDGE → BEWARE → BUILD), and the org lens semantics (shifts AI-feasibility band center by −1/0/+1, never stored, never changes raw scores). It also warns that confidence is sensitivity under a fixed band, not project-success probability, and instructs agents to follow the guidance block rather than substituting their own build-vs-buy prior. This is exceptionally transparent.

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?

The description is long but every section earns its place: input format, resolution behavior, output structure, methodology, confidence semantics, org lens, routing, and clarification handling. It is front-loaded with the core purpose and example, then progressively details methodology and routing. The only minor deduction is that the methodology section is dense and could arguably be trimmed, but for a tool with this complexity, the length is justified.

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?

Given the tool's complexity (banded verdicts, five dimension scores, two axes, urgency, vendors at access depth, guidance blocks, clarification handling, org lens), the description covers all operational aspects an agent needs: input format, resolution fallback, clarification protocol, output contents, confidence interpretation, tie-breaking, and routing to siblings. The output schema exists and the description references its key fields without needing to enumerate them. Nothing critical is missing for correct invocation.

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 schema already documents both parameters thoroughly. The description adds value by explaining the org lens semantics ('shifts the center of the AI-feasibility band by −1 / 0 / +1 and nothing else', 'a filter the caller looks through, never a stored profile', 'choose it from delivery capability, not headcount') and by clarifying the tools array's resolution behavior (resolves by name when indexed, otherwise by description, otherwise clarification.needed). The description also adds the max-100-per-call constraint context and the example format. It doesn't add much beyond the schema for the org parameter since the schema already covers it, but the tools array resolution semantics are genuinely additive.

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 description opens with a specific verb ('Audit a stack') and immediately defines the input shape with a concrete example. It clearly distinguishes this tool from siblings by stating it handles vendor/product names, while b4_recommend handles needs, b4_score handles exact categories, and b4_compare handles build-vs-buy paths. The routing section explicitly names each sibling and its trigger condition, making the purpose unmistakable.

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?

The description provides an explicit routing section: 'a vendor or product name → b4_audit; a need or problem in words → b4_recommend; an exact category name or id → b4_score or b4_compare; browsing/filtering/unknown vocabulary → b4_browse.' It also gives a concrete example of when to add a description ('for anything the index may not know') and instructs how to handle clarification.needed results by relaying askTheUser and re-running with the answer. This is exemplary usage guidance.

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