Skip to main content
Glama

InsideOut (Riley)

by com.luthersystems.insideout

Batch-Inspect GCP Infrastructure

gcpinspect_batch
Read-only

BATCH INSPECTION: run up to 32 GCP inspect probes in one call. ⚠️ PREREQUISITE: Same as gcpinspect — deploy attempt required. Check convostatus for hasDeployAttempt=true before calling.

Use this when you need to check more than ~3 resources. The backend fetches Oracle credentials ONCE per batch and fans out probes against a single GCP credentials blob — a 12-resource health check is ~5–8× faster and 12× fewer Oracle round-trips than calling gcpinspect 12 times.

BUDGETS:

  • Up to 32 sub-probes per call (subs array length).

  • 30s per-sub timeout; 60s total batch wall-clock.

  • Concurrency cap 8.

  • 512 KB response cap: subs past the cap keep their envelope (index/service/action/ok) but have result replaced with truncated=true.

PARTIAL FAILURE IS EXPECTED. The response is an ordered results array; each entry has {index, service, action, ok, result, error}. Inspect each result — do NOT abort on the first error. A credential fetch failure leaves cred-less probes (list-actions, list-metrics) succeeding anyway.

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, use gcpinspect (singular) with action="list-actions" — batch is not the place for discovery. Batch responses are always summarized (no detail/raw per-sub); use singular gcpinspect when you need full metadata or raw API output for one resource.

EXAMPLES:

  • gcpinspect_batch(session_id=..., subs=[ {"service":"compute","action":"list-instances"}, {"service":"gke","action":"list-clusters"}, {"service":"cloudsql","action":"list-instances"}])

  • gcpinspect_batch(session_id=..., subs=[ {"service":"compute","action":"get-metrics","filters":"{"hours":6}"}, {"service":"cloudrun","action":"get-metrics","filters":"{"hours":6}"}])

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
subsYesUp to 32 sub-probes, each with {service, action, filters?, detail?, raw?}. The backend fetches credentials once per batch and fans out probes in parallel (concurrency 8, 30s per-sub timeout, 60s total wall clock). Partial failure is expected — inspect each result.ok independently.
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

A4.9/5.0
Behavior5/5

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses partial failure expectations, credential fetch failure behavior, response truncation at 512 KB, per-sub timeouts, concurrency limits, and response summarization. It also warns about the session token being part of credentials. This is rich behavioral context that goes far beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

The description is long but densely packed with essential information, organized with clear section headers (PREREQUISITE, BUDGETS, PARTIAL FAILURE IS EXPECTED, REQUIRES, EXAMPLES). Every sentence adds value; the core purpose and prerequisite are front-loaded. No redundant text.

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 no output schema, the description explicitly states the response format (ordered results array with index/service/action/ok/result/error) and instructs on handling partial failures. It covers limits, edge cases, supported services, and contrasts with alternatives. This is complete for a complex batch 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 comprehensive descriptions for both session_id (format, prerequisite, token suffix) and subs (maxItems, concurrency, partial failure). The tool description adds examples of valid sub-probe structures and the credential-fetch nuance, providing a bit more context. Since schema coverage is 100%, the baseline is 3, but the description's examples and clarifications justify a 4.

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 'BATCH INSPECTION: run up to 32 GCP inspect probes in one call,' providing a specific verb, resource, and scope. It clearly differentiates from sibling gcpinspect by noting when to use the batch version (more than ~3 resources) and explicitly contrasts with the singular tool for discovery and detailed output.

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 gives explicit when-to-use guidance: 'Use this when you need to check more than ~3 resources' and identifies when not to use it (discovery via list-actions, full metadata/raw output) directing to gcpinspect. It also states the prerequisite (deploy attempt required, check convostatus) and provides performance rationale.

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 targets a distinct domain phase (conversation, inspection, Terraform, versions, feedback) with no functional overlap. The batch variants are clearly optimizations of their singular counterparts.

Naming Consistency4/5

Most tools follow a consistent domain-prefix plus action pattern (e.g., awsinspect, tfdeploy), but 'help', 'submit_feedback', and 'stackdiff' deviate slightly. Overall still readable and predictable.

Tool Count4/5

At 24 tools, the set is slightly large but well-justified given the comprehensive workflow (conversation, cloud inspection, Terraform lifecycle, versioning, feedback). No tools feel superfluous.

Completeness5/5

The tool surface covers the entire infrastructure workflow from design conversation through deployment, inspection, drift detection, rollback, and feedback. No obvious gaps for the stated purpose.

Resources