Retry a failed attempt with resume capabilities, optionally forcing running attempts or overriding parameters to recover from task failures.
Retry a specific failed attempt with resume capabilities
| Name | Required | Description | Default |
|---|---|---|---|
| force | No | Force retry even if attempt is running (default: false) | |
| attempt_id | Yes | Attempt ID to retry | |
| resume_from | No | Task name to resume from (skip successful tasks) | |
| 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 largely drops it: nothing is said about whether a retry creates a new attempt or reuses the ID, whether it is idempotent, what side effects (logs, task re-execution, cost) occur, or what permissions are needed. Since this is a state-changing operation, the absence of any disclosure is a significant gap.
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 short sentence with the core action front-loaded and no filler. It is efficient, though the compactness is partly achieved by omitting information rather than by tight phrasing.
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 tool with no annotations, no output schema, and a nested object parameter whose inner shape is undocumented, the description should explain return/effect semantics and the retry-vs-resume behavior. Instead it stops at ten words, leaving an agent unable to predict what the call produces.
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 description coverage is 100%, so attempt_id, force, resume_from and retry_params are already documented in the schema; baseline is 3. The phrase "resume capabilities" loosely signals resume_from, but the description adds no semantics for force or for the structure of the nested retry_params overrides.
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 ("retry") and resource ("a specific failed attempt"), which tells an agent precisely what the tool acts on. It does not, however, distinguish itself from the sibling retry_session, leaving the attempt-vs-session granularity to be inferred from the name 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?
There is no statement of when to use this versus retry_session, no precondition that the attempt must be in a failed state, and no guidance on when resume_from or force apply. The only usage hint is the word "failed" and the vague "with resume capabilities".
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.