incident-lab
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_incidentsA | List seeded synthetic payment incidents. Read-only. No filters; the catalog is small on purpose. |
| get_paymentA | Fetch one synthetic payment by id (pay_…). Read-only. Does not accept SQL or wildcards. |
| list_job_attemptsA | List settlement-job attempts for one jobId or paymentId. Read-only. |
| search_logsA | Search log lines for one incidentId or paymentId. Optional substring query (max 80 chars). Max 25 lines. No regex, glob, or unscoped search. |
| retry_jobA | The only mutating tool. Re-enqueues a failed job. Requires confirm=true and a written reason. Writes an audit event even when rejected. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a distinct resource and action: incidents, payments, job attempts, logs, and retries. No two tools appear to do the same thing, and their scopes are clearly separated by entity and read-only vs. mutating behavior.
All tool names follow a consistent snake_case verb_noun pattern: list_incidents, get_payment, list_job_attempts, search_logs, retry_job. The verbs are predictable and match the tool's behavior, so an agent can infer the purpose from the name alone.
Five tools is well-scoped for an incident-lab server focused on investigating synthetic payment incidents and retrying failed jobs. Each tool earns its place, and the count is not bloated or too thin for the stated purpose.
The tool set covers the likely investigation workflow: list incidents, inspect payment details, examine job attempts, search logs, and retry a failed job. A dedicated get_incident tool is absent, but list_incidents explicitly says the catalog is small, so this is a minor gap rather than a blocking one.