Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

pipeline_retry_step

Destructive

Retry a failed pipeline step at a given index, then automatically continue executing the remaining steps once it succeeds.

Instructions

Retry a specific failed step in a pipeline, then continue from there.

        Re-runs the step at the given index and, if it succeeds, continues
        executing the remaining steps.

        Args:
            execution_id: The pipeline execution ID.
            step_index: Zero-based index of the step to retry.

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": {
      "execution_id": "<execution_id>",
      "step_index": "<step_index>"
    },
    "name": "pipeline_retry_step"
  }
}

Input Schema

NameRequiredDescriptionDefault
step_indexYesZero-based index of the step to retry.
execution_idYesThe pipeline execution ID.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.5.1
    • addedInput schema / properties / execution_id / description
      Added value: +"The pipeline execution ID."
    • addedInput schema / properties / step_index / description
      Added value: +"Zero-based index of the step to retry."
  2. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Beyond the annotations (which already flag destructiveHint=true, readOnlyHint=false), the description discloses the important downstream behavior: after a successful re-run, the remaining steps continue executing. That is genuine side-effect information an agent would not otherwise have. It still omits what happens if the step is not in a failed state and whether prior completed steps are affected.

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?

The core behavior is front-loaded in the first sentence, and the second sentence clarifies the continuation semantics. The duplicated Args block is minor redundancy against a fully documented schema, but it does not obscure anything.

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 two-parameter mutation tool with no output schema and existing annotations, the description covers what it does, the prerequisite state, and the downstream consequence. Missing pieces like return shape or error behavior are low-cost given the tool's simplicity.

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 the description's Args block simply restates the schema text verbatim ('The pipeline execution ID', 'Zero-based index of the step to retry'). Baseline 3 applies since the schema does all the work and no extra meaning is added.

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 gives a concrete verb and resource ('Retry a specific failed step in a pipeline') plus scope ('at the given index'), so the action is unambiguous. It does not explicitly distinguish itself from the nearby pipeline_resume or pipeline_abort siblings, which is the only thing keeping it from a 5.

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 phrase 'a specific failed step' implies the precondition that the step must have failed, which is useful implied guidance. However, there is no explicit statement of when to choose this over pipeline_resume, nor what to do if the step never failed or the pipeline is still running.

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

Deploy Server

Other Tools