training_resumeResume supervised fine-tuning from a checkpoint by setting total max steps or additional steps to continue training after interruption.
Resume SFT with total max_steps or additional_steps after checkpoint. Spends credits.
| Name | Required | Description | Default |
|---|---|---|---|
| run_id | Yes | ||
| max_steps | No | ||
| num_epochs | No | ||
| idempotency_key | Yes | ||
| additional_steps | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false (a mutation) and idempotentHint=true, so the safety profile is partly covered. The description adds two useful facts beyond annotations: it spends credits and requires a prior checkpoint. It omits what happens to prior progress, permission needs, or failure behavior.
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?
Two dense sentences with no waste. The core action and its parameter choice are front-loaded, and the cost warning follows. Every clause earns its place.
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?
An output schema exists, so return values need not be explained, and the checkpoint/credit notes are valuable. Still, as a credit-spending mutation with 0% schema coverage, the description leaves num_epochs and idempotency_key semantics and the interaction between max_steps and num_epochs unexplained.
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 0% for 5 parameters. The description names max_steps ('total') and additional_steps (incremental) and clarifies their semantic difference, which is genuinely helpful. But run_id, num_epochs, and idempotency_key get no explanation, leaving most parameters undocumented.
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+resource ('Resume SFT') and distinguishes itself from the training_start/train_sft siblings by implying continuation rather than initiation. The acronym 'SFT' and lack of explicit sibling naming keep 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'after checkpoint' implies the prerequisite state (a checkpoint must exist) and it surfaces the max_steps-vs-additional_steps choice. However, it never states when to use this over training_start or training_stop, nor any exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.