Skip to main content
Glama

Retry data run

retry_data_run
Destructive

Retry a FAILED backup, restore or clone (the twin of ankra runs retry). A fresh run resumes from the step that failed; the failed run is kept as evidence of what went wrong. Only a failed run can be retried. Requires runs.operate and backups.operate.

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": {
      "run_id": "<run_id>"
    },
    "name": "retry_data_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idYesRun id (UUID) of the failed run, from list_data_runs.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag a non-read-only, non-idempotent operation; the description adds substance beyond them: a new run is created that resumes from the failed step, the failed run is preserved as evidence, and two specific permissions (runs.operate, backups.operate) are required. There is mild tension with destructiveHint=true (the original run is said to be kept), but since the retried backup/restore/clone itself can overwrite data, this reads as nuance rather than contradiction.

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?

Three tight sentences: eligibility first, then side effects, then the failure precondition, then permissions. The CLI-parity note is short and aids recognition; nothing is repeated or padded.

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?

For a single-parameter mutation with no output schema, it covers preconditions, side effects and auth needs, which is most of what an agent needs. It does not say what calling it returns (e.g., a new run id) or how to track the fresh run afterwards, which matters given there is no output schema.

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?

With one fully documented parameter, the schema already carries the syntax; the description adds a real constraint — the run_id must reference a run in failed state, sourced from list_data_runs. That restricts the valid value domain in a way the schema does not.

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 ('Retry a FAILED backup, restore or clone') and scopes the resource to the failure-recovery case, which separates it from cancel_data_run/get_data_run. It does not explicitly differentiate from the other retry_* siblings (retry_application, retry_execution, retry_pipeline_run), leaving that inference to the resource noun.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit use condition — 'Only a failed run can be retried' — which is exactly the eligibility gate an agent needs, plus implicit guidance that successful or in-flight runs should go elsewhere. It stops short of naming which sibling to use for non-failed runs or when to cancel instead.

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.