Skip to main content
Glama

InsideOut (Riley)

by com.luthersystems.app

Inspect GCP Infrastructure

gcpinspect
Read-only

INSPECTION: Inspect GCP infrastructure for a deployed project ⚠️ PREREQUISITE: This tool requires a prior deployment ATTEMPT (successful or failed). Check convostatus for hasDeployAttempt=true before calling. Works even after failed deploys to inspect orphaned resources.

Inspect deployed GCP resources after a deployment attempt. Use this tool when the user asks about the status or details of their deployed GCP infrastructure. It fetches temporary read-only credentials securely and queries the GCP API directly.

RESPONSE TIERS (default is summary for token efficiency):

  • Summary (default): Key fields only (~500 tokens). Set detail=false, raw=false or omit both.

  • Detail: Full metadata for a specific resource. Set detail=true + resource filter.

  • Raw: Complete unprocessed API response. Set raw=true.

REQUIRES: session_id from convoopen response (format: sess_v2_...). Supported services: apigateway, bastion, billing, certificatemanager, cloudarmor, cloudbuild, cloudcdn, clouddeploy, clouddns, cloudfunctions, cloudkms, cloudlogging, cloudmonitoring, cloudrun, cloudsql, compute, firestore, gcs, gke, iam, identityplatform, loadbalancer, memorystore, pubsub, secretmanager, vertexai, vpc For a specific service's actions, call with action="list-actions".

METRICS: Use list-metrics to see available Cloud Monitoring metrics for any service (no credentials needed — progressive disclosure). Use get-metrics to retrieve time-series data. Optional filters JSON: {"hours":6,"period":300}. Label breakdowns: Cloud Functions (by status), Load Balancer/API Gateway (by response_code_class), Cloud CDN (by cache_result). Secret Manager get-metrics returns operational health (version count, replication, create time) — no time-series. Bastion is an alias for Compute Engine metrics (SSH connection count not available as a GCP metric). BILLING: Use service=billing to inspect GCP billing. Actions: get-billing-info (check if billing enabled, which billing account), get-budgets (list budget alerts for the project — auto-fetches billing account). Requires roles/billing.viewer IAM role. Required IAM roles: Monitoring Viewer (roles/monitoring.viewer) for metrics, Secret Manager Viewer (roles/secretmanager.viewer) for secret health, Billing Viewer (roles/billing.viewer) for billing.

EXAMPLES:

  • gcpinspect(session_id=..., service="compute", action="list-instances")

  • gcpinspect(session_id=..., service="gke", action="list-clusters")

  • gcpinspect(session_id=..., service="cloudsql", action="get-metrics", filters="{"hours":6}")

  • gcpinspect(session_id=..., service="billing", action="get-billing-info")

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
rawYesWhen true, returns the unprocessed GCP API response. Escape hatch for fields the summarized response doesn't surface.
actionYesOperation on the service. Examples: 'list-instances' (compute), 'list-buckets' (storage), 'list-clusters' (gke), 'list-actions' (discovery), 'list-metrics' / 'get-metrics' (Cloud Monitoring).
detailYesWhen true, returns full metadata for a single resource. When false (default), returns a summary.
filtersYesOptional JSON-encoded filter object passed through to the underlying GCP API. Examples: '{"hours":6}' for metric windows, '{"zone":"us-central1-a"}' for zone-scoped queries.
serviceYesGCP service to query. Examples: 'compute', 'storage', 'cloudsql', 'gke', 'cloudrun', 'pubsub', 'firestore'. Use action='list-actions' to discover supported actions for a service.
session_idYesSession ID from convoopen — pass back EXACTLY as returned, including the ?token=... suffix (format: sess_v2_*?token=*). The suffix is part of the session credential; never strip it when summarizing. The session must have a GCP deploy attempt before inspect probes will succeed.

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses that it fetches temporary read-only credentials securely, works after failed deploys to inspect orphaned resources, reverts to a summary by default for token efficiency, lists required IAM roles, and explains specific metric behaviors (e.g., Secret Manager returns operational health without time-series, Bastion is an alias with limitations). This is rich behavioral context.

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 well-structured with clear sections (PREREQUISITE, RESPONSE TIERS, METRICS, BILLING, EXAMPLES) and is front-loaded with the core purpose. It is long but every section provides substantive information. Minor repetition at the start ('INSPECTION', 'Inspect GCP infrastructure', 'Inspect deployed GCP resources') costs it a full 5.

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?

For a complex tool with 6 required parameters, no output schema, and many supported services, the description is remarkably complete. It covers prerequisites, response tier behaviors, IAM role requirements, billing specifics, metric breakdowns, and edge cases like failed deployments and orphaned resources. This is more than sufficient for an agent to correctly invoke the tool.

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?

The schema already provides 100% parameter coverage with descriptions and examples, so the baseline is 3. The description adds valuable nuances: the response-tier semantics for detail/raw, filter JSON examples, the explicit instruction to pass session_id exactly as returned, and service-specific action hints. This exceeds the baseline without redundancy.

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 starts with 'INSPECTION: Inspect GCP infrastructure for a deployed project' and later states 'Inspect deployed GCP resources after a deployment attempt.' This clearly identifies a specific verb (inspect), resource (GCP infrastructure), and scope (post-deployment). It also distinguishes itself from siblings like awsinspect (AWS counterpart) and gcpinspect_batch (batch variant).

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 explicitly says 'Use this tool when the user asks about the status or details of their deployed GCP infrastructure.' It provides a prerequisite (hasDeployAttempt=true), references convostatus for verification, and includes concrete usage examples for services and actions. It also advises using action='list-actions' for discovery, which is a clear usage pattern.

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

All InsideOut (Riley) toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose, with clear domain prefixes (convo*, tf*, stack*, aws/gcp inspect) separating conversation, deployment, versioning, and cloud inspection. The batch variants (awsinspect_batch, gcpinspect_batch) are explicitly scoped as higher-throughput versions of their singular counterparts, so no ambiguity exists.

Naming Consistency4/5

The naming is mostly consistent: lowercase concatenated verb_noun patterns dominate (convoopen, tfdeploy, stackrollback, awsinspect). However, submit_feedback uses snake_case, and help stands alone as a generic utility, breaking the otherwise uniform lowercase-concatenated style.

Tool Count4/5

24 tools is on the heavier side, but the count is justified by the breadth of the domain: conversation workflow, multi-cloud inspection, Terraform lifecycle, stack versioning, and utilities. Each tool fills a distinct role, so while slightly high, the count is not bloated.

Completeness5/5

The tool surface covers the full infrastructure lifecycle: conversation and design (convoopen/convoreply/convostatus), Terraform generation and deployment (tfgenerate/tfplan/tfdeploy), monitoring (tfstatus/tflogs), teardown (tfdestroy), drift detection, stack versioning, and cloud inspection. No critical dead ends; only a missing explicit cancel/abort for running jobs is a minor gap.

Resources