List models, datasets, logs, metrics, and reports produced by a job. Provide a job ID for a specific job, or omit it to include all jobs.
List artifacts (models, datasets, logs, metrics, reports) produced by a job, or all jobs if job_id is omitted.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that it lists artifacts but doesn't clarify whether the tool is read-only or if it might trigger side effects. It also doesn't mention pagination, sorting, or result limits. The behavior is minimally described; an agent might not know if this is a safe read operation or if it could be expensive.
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?
The description is a single sentence that is efficient and front-loaded with the main action and resource. It includes the parenthetical list of artifact types and the conditional scope. 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 simple listing tool with one optional parameter and no output schema, the description provides enough to call it correctly. However, given the complexity of the Colab environment and the absence of output schema, it could benefit from mentioning that the output is a list of artifacts and perhaps that some artifacts might not be available if jobs are still running. The absence of any behavioral details is a minor gap.
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 has 1 parameter with 0% description coverage)Skip 5; the definition portion accomplish the description. It explains that job_id filters to a specific job and that omitting it lists all jobs. This adds meaning beyond the schema, which only shows 'string' type. The description effectively documents the parameter's semantics.
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 description clearly states the verb 'List' and the resource 'artifacts', and enumerates the artifact types (models, datasets, logs, metrics, reports), which distinguishes it from sibling tools like colab_get_logs and colab_get_job. It also mentions the optional job_id scope, which adds precision. However, it doesn't explicitly contrast with siblings, but the resource listing is specific enough.
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 description implies usage context by mentioning that job_id is optional, suggesting it can list all jobs or a specific job's artifacts. But it doesn't explicitly state when to choose this tool over alternatives (e.g., colab_get_logs for logs only, colab_get_job for job details). No exclusions or alternative names are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.