Skip to main content
Glama

architect_panel

Read-onlyIdempotent

Convenes architect personas on a subject to return role-specific questions, checks, deliverables, and workbench tools for architecture reviews.

Instructions

Convene architect personas (solution, enterprise, business, data, infrastructure, software, AI, security, governance, FinOps) on a subject: each returns its questions, checks, deliverables and the workbench tools to call. Lens, not a verdict.

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": {
      "subject": "<subject>",
      "artifactType": "<artifactType>"
    },
    "name": "architect_panel"
  }
}

Input Schema

NameRequiredDescriptionDefault
rolesNo
subjectYes
knownFactsNo
artifactTypeYes

Output Schema

NameRequiredDescriptionDefault
kindNo
panelNo
sourcesNo
subjectNo
howToUseNo
synthesisNo
validatedNo
knownFactsNo
limitationNo
artifactTypeNo
availableRolesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.0
    • changedInput schema / required
      Previous value: -[
      -  "subject",
      -  "artifactType",
      -  "roles",
      -  "knownFacts"
      -]New value: +[
      +  "subject",
      +  "artifactType"
      +]
  2. First observedv0.4.1

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description only needs to add context. It does disclose the shape of the response — per-role questions, checks, deliverables, and recommended workbench tools — which is useful for an orchestration agent deciding how to chain calls, but it says nothing about cost, latency, determinism, or behavior when roles are omitted (default of three roles is only in the schema).

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?

Two compact segments, front-loaded with the verb and resource, and the role list earns its space by mirroring the roles enum. The only mild waste is that the persona list is long enough to delay the more actionable output clause to the end.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Return values are covered by the output schema and safety by annotations, so the remaining gap is caller-side semantics — and with 2 required parameters at 0% schema coverage the description leaves an agent guessing about artifactType and knownFacts. For a tool whose usefulness depends on supplying the right subject framing and facts, this is a meaningful omission.

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

Parameters2/5

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

Schema description coverage is 0%, so the description carries full burden for four parameters and largely fails to. It enumerates the role names that map onto the roles enum, but never explains what 'subject' should contain, what 'artifactType' controls (does it change each persona's checks?), or what 'knownFacts' does — none of these are inferable from the bare enum and string types.

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 gives a specific verb and resource ('Convene architect personas'), enumerates all ten persona roles, and states what each returns (questions, checks, deliverables, workbench tool calls). The tagline 'Lens, not a verdict' implicitly separates it from the review/verdict siblings (well_architected_review, threat_model, code_review_architecture), but no sibling is named outright.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Lens, not a verdict' hints at the intended use — gathering perspectives before a decision rather than producing a sign-off — and 'on a subject' implies an early, exploratory stage. However there is no explicit when-to-use, no when-not-to-use against the many review/plan siblings, and no guidance on whether this should precede or follow tools like implementation_plan or threat_model.

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