artifacts

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

There are no annotations, so the description carries the full behavioral burden. It only states the listing action and artifact format; it does not disclose whether the call is read-only, what identifiers are needed, whether results are paginated, or what the response contains.

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 front-loaded sentence with no filler. It loses one point because 'opaque artifact IDs' is jargon that adds little to an agent's understanding.

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 one-parameter tool with an output schema, the description conveys the basic operation and lets an agent infer the input. However, it omits parameter semantics and usage context, so it is only minimally complete.

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%, and the description barely compensates. 'Produced by a run' weakly implies run_id identifies the run, but it does not explain how to obtain the run_id, its format, or what 'opaque artifact IDs' means in practice.

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 uses a specific verb ('List') and a specific resource ('JSONL artifacts produced by a run'), making the core operation identifiable. It is reasonably distinct from sibling tools like runs, logs, and result, though the phrase 'opaque artifact IDs' is mildly confusing rather than clarifying.

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 guidance is given about when to choose artifacts over siblings like collect, result, logs, export, or preview. The description implies it is for per-run artifact listing but does not state any selection criteria or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.