Skip to main content
Glama

Second Wind AI

cross account events never arrive

eventbridge-cross-account-delivery-trace
Read-onlyIdempotent

Send one sample event, the sending rule, the receiving bus policy, the receiving rules and target policies. Walks the event through all five places cross account delivery stops silently, with real EventBridge pattern matching, and returns the first blocking stage, the exact field or statement responsible, and the command or statement that fixes it. Use when the error reads: events sent to another account never arrive | rule shows Invocations but target never runs | FailedInvocations metric above zero | rule on the receiving bus never triggers. Covers: Bus to bus delivery between two accounts with supplied rules and policies. Lambda, SQS and SNS target policies are evaluated; role based targets are reported as unchecked. API destinations and Pipes are not covered. Price: 8.00 USDC on Base via x402, charged only when the case is solved.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "sample_event": "<sample_event>",
      "source": "<source>",
      "destination": "<destination>"
    },
    "name": "eventbridge-cross-account-delivery-trace"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourceYes
contextNoKnown context keys such as aws:PrincipalOrgID.
destinationYes
sample_eventYesOne event exactly as the sender publishes it (source, detail-type, detail, resources). account and region are filled from source if absent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds substantive behavior beyond them: a five-stage traversal using real EventBridge pattern matching, the exact return payload (first blocking stage, responsible field or statement, remediation command), explicit coverage gaps (API destinations and Pipes excluded; role-based targets unchecked), and a pricing policy (8.00 USDC on Base via x402, charged only when the case is solved). The one slight ambiguity is "Send one sample event," which could read as publishing; the surrounding text implies offline replay, so this is not a genuine contradiction with readOnlyHint.

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?

Front-loaded with the action and the failure modes, then coverage limits, then price — a sensible order with almost no filler. The opening sentence is a comma-spliced fragment list that takes a second read to parse, and the pricing sentence is long, but every clause carries operational 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?

No output schema exists, and the description compensates by naming exactly what comes back: the first blocking stage, the exact field or statement responsible, and the fixing command. Combined with the coverage exclusions and pricing, an agent knows what it will get and what it costs. Minor gap: it does not say what is returned when no blocking stage is found (i.e., the delivery is clean).

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?

Schema coverage is only 50%, so the description must carry weight, and it does: it enumerates the input bundle (sample event, sending rule, receiving bus policy, receiving rules, target policies) and explains their role as the five checkpoints, plus notes that role-based targets are reported as unchecked, which maps directly to the target_role parameter. This gives the agent a mental model for assembling nested objects rather than just field names.

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 names a specific action and object: it takes one sample event plus the sending rule and receiving policies/rules, walks the event through all five places cross-account delivery can stop, and returns the first blocking stage with the responsible field and a fix. That is a concrete verb-plus-resource statement an agent can distinguish from the sibling diagnostic tools (VPC egress, IAM layers, SG dependencies) without opening a schema.

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?

Usage is pinned to explicit error signatures: "events sent to another account never arrive | rule shows Invocations but target never runs | FailedInvocations metric above zero | rule on the receiving bus never triggers." The description also states the boundary conditions — API destinations and Pipes are not covered, role-based targets are reported as unchecked — so the agent knows both when to select it and where it will come up short.

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