Download job logs from a SkyPilot cluster to a local directory, returning a mapping of job IDs to log file paths. Use it to retrieve and inspect cluster job output.
Download job logs from a cluster to a local directory. Returns a mapping of job IDs to local log file paths.
| Name | Required | Description | Default |
|---|---|---|---|
| job_ids | No | ||
| cluster_name | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
readOnlyHint=true is already supplied by annotations, so the safety profile is covered. The description does add that files land in a local directory and that a job-ID-to-path mapping is returned, but it omits key behavior: what happens when job_ids is null, and whether existing local files are overwritten. Consistent with annotations, no contradiction.
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 tight sentences, front-loaded with the action and followed by the return shape. No wasted clauses, though it is on the terse side for a tool with unstated parameter behavior.
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 the return-value sentence is somewhat redundant, and the description omits the two things an agent actually needs: how to pick among the sibling download_logs tools and what a null job_ids means. Adequate but with clear gaps for a tool in a crowded family.
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% for both parameters, so the description must carry the load. It implicitly references job IDs via the return mapping but never explains that job_ids selects which logs to fetch or that a null default means all jobs; cluster_name is not explained either (though self-evident).
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 ('download job logs from a cluster') and even names the destination ('to a local directory'), which is more than a tautology. However, it does not differentiate itself from the four sibling download tools (managed_job_download_logs, serve_download_logs, pool_download_logs), so an agent cannot tell which of them applies to a plain cluster job without opening each schema.
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?
No when-to-use guidance is given, and critically no distinction from skypilot_managed_job_download_logs / serve_download_logs / pool_download_logs, which share nearly the same name pattern. The agent is left to infer that 'cluster' jobs are the scope.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.