Restart a failed session from the beginning or resume from a specific task, with optional parameter overrides. Use it to recover interrupted Treasure Data workflows without starting over.
Retry a failed session from the beginning or a specific task
| Name | Required | Description | Default |
|---|---|---|---|
| from_task | No | Task name to retry from | |
| session_id | Yes | Session ID | |
| retry_params | No | Override parameters for retry |
Changes observed during successful MCP inspections.
v0.5.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden, and it falls short. It does not say whether retrying creates a new attempt, what happens to the prior failed attempt's state, whether the call is synchronous or queued, or what permissions/conditions are required to retry.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with the two retry modes stated compactly and no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation-style action tool with no annotations, no output schema, and a free-form nested retry_params object, the description is too thin. It says nothing about the return value (e.g., a new attempt ID), success/failure conditions, or how retry_params is shaped.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3, but the description earns an extra point by clarifying that omitting from_task retries "from the beginning" — semantics the schema's "Task name to retry from" does not convey. retry_params is left unexplained, but the schema covers it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource (retry a session) plus the two modes of retry (from start or from a task). It distinguishes itself reasonably from retry_attempt by operating on sessions, but never explicitly contrasts with that sibling, which a reader must infer from the names alone.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
"Retry a failed session" implies a precondition (session must have failed), but the description never states that as a requirement, nor does it route the agent between retry_session, retry_attempt, and kill_attempt. Usage is inferable but not spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.