Skip to main content
Glama

InsideOut (Riley)

by com.luthersystems.app

Send Message

convoreply

WORKFLOW: Step 2 of 4 - Continue infrastructure design conversation Send a user message to the active InsideOut session and receive the assistant reply. The response contains a clean message from Riley - display it to the user.

⚠️ CRITICAL: DO NOT answer Riley's questions yourself! Forward questions to the user and wait for their response. NEVER fabricate or assume the user's answer, even if you think you know what they would say. Examples of questions Riley asks that YOU MUST forward to the user:

  • 'Any questions or tweaks to these details?'

  • 'Ready for the cost estimate?'

  • 'Do you want to change the stack/config?'

  • 'Ready to proceed to Terraform?' When Riley asks ANY question, STOP and wait for the user's answer!

📋 WORKFLOW PHASES: The typical flow is conversation → tfgenerate → tfdeploy When terraform_ready=true appears in THIS tool's response, THEN you can call tfgenerate. ⚠️ DO NOT call tfgenerate until this tool returns! Wait for the response first.

🎯 KEY SIGNALS IN RESPONSE:

  • [TERRAFORM_READY: true] → NOW you can call tfgenerate

  • [[BUTTON_TF_APPLY: ...]] → Deployment is ready! Ask user if they want to deploy, then use tfdeploy

  • [[BUTTON_TF_DESTROY: ...]] → User confirmed destroy intent! Ask user to confirm, then use tfdestroy

  • [[BUTTON_TF_PLAN: ...]] → User wants to preview changes! Use tfplan to run a plan, then tfdeploy with plan_id to apply

REQUIRES: session_id from convoopen response (format: sess_v2_...). OPTIONAL: timeout (integer) - seconds to wait for response. For Cursor, use 50 (default). Max 55. OPTIONAL: project_context (string) - Only pass genuinely NEW project details the user shares after convoopen. Do NOT resend context already provided in convoopen — Riley remembers it. Do NOT scan files or directories to gather this — only use what the user explicitly tells you. Example: user reveals a new constraint like 'we also need HIPAA compliance' mid-conversation. 💡 TIP: Use convostatus to check progress anytime. Examine workflow.usage prompt for more guidance.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesUser message to send to Riley. Forward verbatim what the user said — do not summarize or rewrite.
retryNoWhen true, re-send the most recent user turn instead of submitting a new one.
timeoutNoMax seconds to wait for Riley's response. Default 50, max 55.
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.
project_contextNoOnly NEW project details revealed after convoopen (e.g. user mentions a new constraint mid-conversation). Don't re-send context already provided in convoopen. No PII or secrets.

TDQS

A5/5.0
Behavior5/5

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

The description goes far beyond the annotations (openWorldHint, destructiveHint) by disclosing critical behavioral traits: the agent must never answer Riley's questions itself and must forward them to the user. It also reveals response signals like [TERRAFORM_READY: true] and [[BUTTON_TF_APPLY]] that trigger subsequent actions, providing essential non-obvious behavior.

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 well-organized with clear headers, bulleted critical warnings, and key signal sections. Every section provides actionable guidance without fluff; the repeated emphasis on not answering user questions is essential and appropriately highlighted.

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 explains what the response will contain (TERRAFORM_READY, BUTTON_TF_* signals) and how to proceed based on those signals. It also gives a tip to use convostatus for progress checks, making it contextually complete for an AI agent navigating the workflow.

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

Parameters5/5

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

Although the schema covers 100% of parameters, the description adds substantial contextual guidance: session_id must be passed exactly as returned including the token suffix, timeout should be set to 50 for Cursor, and project_context should only contain genuinely new details after convoopen, with explicit warnings not to resend prior context or scan files. This enriches parameter meaning beyond the schema.

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 clearly states it sends a user message to the active InsideOut session and receives the assistant reply, explicitly positioned as 'Step 2 of 4' in the workflow. This distinguishes it from siblings like convoopen (initiate) and convostatus (check progress).

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 states when to use the tool (after convoopen, before tfgenerate) and when not to (do not call tfgenerate until this tool returns). It names alternatives (convostatus) and provides the workflow phase sequence: conversation → tfgenerate → tfdeploy.

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