list_run_artifacts

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

With no annotations, the description carries the behavioral burden. It discloses that the tool returns only metadata-like artifact information, not artifact contents, via 'paths, hashes, media types, and sizes only.' However, it does not mention access requirements, pagination, or behavior if the run_id is invalid.

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. Every word earns its place, and the 'only' qualifier adds useful limitation information without redundancy.

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?

The tool is simple, has one required parameter, and an output schema exists, so return-value documentation is unnecessary. Still, the missing run_id semantics and absent usage guidance leave minor but real gaps for an agent deciding whether and how to call it.

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?

The schema has 0% description coverage, so the description must compensate. It never explains that run_id identifies the run whose artifacts should be listed; the only clue is the self-explanatory property name, which is not enough for a low-coverage schema.

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?

Description uses a specific verb ('List') and resource ('artifacts'), and explicitly enumerates the returned attributes: paths, hashes, media types, and sizes. The trailing 'only' clearly scopes the tool away from sibling operational tools like doctor, start_run, or get_run_summary.

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 use this tool versus related alternatives such as get_run_summary or inspect_model. The description states what it lists but not when an agent should choose it.

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