Skip to main content
Glama
vmware-skills

vmware-pilot

by vmware-skills
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

review_workflow

Read-onlyIdempotent

Validate a planned workflow before execution to catch delete-then-use errors, missing parameters, cross-skill ordering issues, and missing approval gates.

Instructions

[READ] Sanity-check a planned workflow before execution.

Performs structural validation only — does NOT call into other skills. Catches the common authoring errors before they hit production:

  • Delete-then-use: a step deletes resource X, a later step references X

  • Missing required params: a step has empty params or placeholder values

  • Cross-skill order issues: surfacing the cross-skill dispatch sequence

  • Risk profile: count of destructive / write / read-only / unclassified steps

  • Approval coverage: is every destructive OR unclassifiable step gated behind a preceding require_approval?

Each step is placed in a tier from the tool's entry in get_skill_catalog first, then from name patterns. A step that matches neither is reported as ungated_unclassified rather than assumed safe: pilot dispatches nothing itself and cannot inspect a sibling skill's annotations, so "this tool is unknown to me" is the honest finding, and it needs the same gate a known destructive step does. The remedy is in the message — add the tool to SKILL_CATALOG with the risk its own skill declares, or add a gate.

Medium-risk writes (create / scale / enable) are classified and counted but not gated: the family gates destructive work, and several built-in templates deliberately create in staging before asking for approval.

Returns: Dict with keys: - verdict: "approved" if no structural issues, otherwise "needs_revision" - findings: list of {severity, kind, message, step_index}. Kinds ungated_destructive, ungated_unclassified and destructive_in_parallel_group are what run_workflow refuses on; force=True overrides that only for a built-in template, never for a custom workflow's missing approval gate. - summary: counts — total/destructive/write/read_only/approval_gates, parallel_groups, est_duration_min, plus classified_steps and unclassified_steps so an "approved" verdict can be told apart from a workflow this review could not read.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
workflow_idYesThe workflow ID returned by ``create_workflow_from_template``.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.3.0
    • changedInput schema / properties / workflow_id / description
      Previous value: -"The workflow ID returned by ``plan_workflow``."New value: +"The workflow ID returned by ``create_workflow_from_template``."
  2. Changed2 schema fields changedv1.11.1
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / workflow_id / description
      Added value: +"The workflow ID returned by ``plan_workflow``."
  3. First observedv1.5.22

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), and the description adds substantial behavior beyond them: no cross-skill calls, tier-based classification, the deliberate decision not to gate medium-risk writes, the honest 'ungated_unclassified' fallback, and the force=True limitation for custom workflows. This is exactly the kind of non-obvious behavior an agent needs and cannot infer from 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then organized as a scannable bullet list of the exact error classes caught, followed by a returns contract. It is longer than most descriptions, but nearly every line carries decision-relevant content; only minor prose (e.g. the medium-risk write rationale) could be tightened.

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?

Despite having no output schema, the description fully specifies the return dict (verdict, findings kinds, summary counts) and explains which finding kinds cause run_workflow to refuse. Combined with the classification and gating rules, an agent has everything needed to call this and interpret its result.

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?

There is a single required parameter with 100% schema description coverage, so the schema already documents workflow_id (the ID returned by create_workflow_from_template). The description adds no format, provenance, or constraint detail beyond that, so the baseline 3 applies.

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?

Opens with a specific verb+resource and an explicit scope qualifier ('[READ] Sanity-check a planned workflow before execution') and immediately bounds what it is not ('structural validation only — does NOT call into other skills'). An agent can distinguish it from design_workflow, run_workflow, and get_workflow_status 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?

The timing condition is stated clearly ('before execution') and the description ties findings to run_workflow's refusal behavior plus the force=True escape hatch, which effectively tells the agent when a review is load-bearing. It stops short of naming sibling alternatives (e.g. design_workflow / create_workflow_from_template) as the things to do first, so it is strong context rather than a full when/when-not routing statement.

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

Deploy Server

Other Tools