training_logsRetrieve bounded recursive training logs or read from an artifact path using a byte cursor to monitor and debug fine-tuning, RL, and evaluation runs by run ID.
Read bounded recursive logs, or an artifact path with a byte cursor.
| Name | Required | Description | Default |
|---|---|---|---|
| cursor | No | ||
| offset | No | ||
| run_id | Yes | ||
| max_lines | No | ||
| artifact_path | 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 and idempotentHint, lowering the bar. The description adds genuine context beyond them by disclosing two access modes (bounded recursive log reads vs. artifact-path reads with a byte cursor), but says nothing about auth, limits, or what the cursor returns.
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 compact, front-loaded sentence with no filler. It is appropriately sized, though its brevity borders on cryptic rather than crisp.
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 described, but with 5 parameters at 0% schema coverage and no annotation-derived param detail, the description leaves the calling contract largely undefined for the agent.
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 0% across 5 parameters, so the description must carry the load. It only loosely gestures at artifact_path and cursor; run_id, offset, and max_lines (the bound implied by "bounded") are never explained in either place.
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?
The verb+resource ("Read ... logs") is identifiable, but the object is garbled: "bounded recursive logs, or an artifact path with a byte cursor" reads as two half-merged modes. It gives no differentiation from siblings like training_metrics, training_get, or session_trace_export.
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 explicit when-to-use, when-not-to-use, or named alternative among the ~48 siblings. The phrase "or an artifact path" hints at a second mode but never states when to pick it over the default recursive-log mode.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.