Skip to main content
Glama

Write up an AI incident

review_ai_incident
Read-onlyIdempotent

A blameless post-incident review for an AI feature: where it failed (input, retrieval, prompt, model, tools, output checks), why evals and monitoring missed it, actions, and the new eval cases that would catch it next time. Returns instructions to follow with the user's text.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "review_ai_incident"
  }
}

Input Schema

NameRequiredDescriptionDefault
incidentNoWhat the feature does, what went wrong, and what's known so far

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. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds the genuinely useful detail that it 'Returns instructions to follow with the user's text' — i.e. output is a guided template, not a completed analysis. That resolves an ambiguity annotations alone cannot. It does not discuss length limits or handling of sparse input.

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?

One compact sentence with the framing front-loaded and the failure taxonomy in the middle; no filler. It is slightly dense as a single run-on clause chain, but every phrase carries information.

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 return-value explanation is not required, and the description still notes that the return is instructions. Combined with the covered analysis dimensions and the 100%-documented parameter, an agent has enough to call it correctly; only the explicit sibling comparison is missing.

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?

Schema coverage is 100% and the single parameter already documents 'what the feature does, what went wrong, and what's known so far'. The description adds value by implying the fuller structure the incident narrative should cover (failure stage, eval gaps, actions), guiding what to supply beyond the terse schema wording.

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?

States a specific verb and resource — 'a blameless post-incident review for an AI feature' — and enumerates the analysis dimensions (input, retrieval, prompt, model, tools, output checks, eval/monitoring gaps, actions, new eval cases). This clearly separates it from review_ai_spec and review_launch_readiness, though it never names those siblings explicitly.

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?

The word 'post-incident' implies the trigger condition, but the description never states when to use this versus review_ai_spec, review_launch_readiness, or design_eval_suite, nor any prerequisites (e.g. that an incident has already occurred). Usage is inferable but not explicit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources