Skip to main content
Glama

AI PM Lab

by io.aipmlab
OverviewDiscussionsAdmin

Replay a recorded experiment

replay_experiment
Read-onlyIdempotent

What happened in one recorded real run (e.g. whether a prompt injection leaked data with given defences, or how many answers were made up without a facts sheet): the setup, each step, the result and the model's reply, with a link to run it on the site.

Input Schema

NameRequiredDescriptionDefault
runYesThe run's number from list_experiments
pageYesA 3D page (injection, rag, evals, agent-loop, next-token, embeddings) or a lesson's slug (e.g. prompt-injection, model-routing, hallucination-and-grounding, human-in-the-loop)

Output Schema

NameRequiredDescriptionDefault
textYesThe answer in markdown, as shown to the user; for the guides, instructions to follow with the user's text
linksYesThe AI PM Lab pages the answer links to, where each idea can be tried hands-on

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "links": {
+      "description": "The AI PM Lab pages the answer links to, where each idea can be tried hands-on",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "text": {
+      "description": "The answer in markdown, as shown to the user; for the guides, instructions to follow with the user's text",
+      "type": "string"
+    }
+  },
+  "required": [
+    "text",
+    "links"
+  ],
+  "type": "object"
+}
  2. Changed2 schema fields changed
    • changedInput schema / properties / page / description
      Previous value: -"injection (prompt injection defences), rag (retrieval), evals (graders), agent-loop, next-token, embeddings"New value: +"A 3D page (injection, rag, evals, agent-loop, next-token, embeddings) or a lesson's slug (e.g. prompt-injection, model-routing, hallucination-and-grounding, human-in-the-loop)"
    • changedInput schema / properties / page / enum
      Previous value: -[
-  "injection",
-  "rag",
-  "evals",
-  "agent-loop",
-  "next-token",
-  "embeddings"
-]New value: +[
+  "injection",
+  "rag",
+  "evals",
+  "agent-loop",
+  "next-token",
+  "embeddings",
+  "how-ai-agents-work",
+  "how-llms-work",
+  "retrieval-augmented-generation",
+  "embeddings-and-semantic-search",
+  "prompt-caching-and-cost",
+  "multi-agent-systems",
+  "prompt-injection",
+  "ai-evals",
+  "prompting-vs-rag-vs-fine-tuning",
+  "human-in-the-loop",
+  "hallucination-and-grounding",
+  "production-monitoring",
+  "writing-good-prompts",
+  "reasoning-models",
+  "model-routing",
+  "structured-outputs",
+  "tool-design-and-mcp",
+  "workflows-vs-agents"
+]
  3. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, closed-world behavior, so the safety profile is covered. The description adds value by enumerating what the record contains (setup, each step, result, the model's reply, a run-on-site link), which is real context beyond the annotations. It does not clarify pagination or output size limits.

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?

A single front-loaded sentence with no filler; the enumeration of returned content earns its place. It could be tightened slightly, but there is no wasted text.

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

Completeness4/5

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

An output schema exists, so the description need not detail return values, and it correctly focuses on what the record represents plus the link to run it live. Combined with full schema coverage and read-only annotations, this is nearly complete for a two-param read tool.

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?

Schema coverage is 100%, and both params are self-documenting ('run's number from list_experiments', page enum of 3D pages vs lesson slugs). The description adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 makes clear this surfaces the full detail of a single recorded run (setup, steps, result, model reply, link), which is more specific than the bare name 'replay'. It does not explicitly name the sibling it complements (list_experiments), though 'one recorded real run' implicitly contrasts with a list operation.

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?

Usage is implied rather than stated: the parenthetical examples (prompt injection, hallucinated answers) suggest when this is useful, and the 'run' param ties it to list_experiments. However, there is no explicit when-to-use/when-not guidance or named alternative, so it stays at minimum-viable.

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

All AI PM Lab toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources