list_artifacts

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

With no annotations, the description carries the burden of behavioral disclosure. It usefully reveals that large TDR files are not read into model context, suggesting a low-cost listing operation. However, it does not clarify return behavior, side effects, or whether the index is up-to-date.

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 one concise sentence, front-loads the purpose, and adds a useful caveat without 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 one-parameter listing tool, the description covers the central caveat but leaves gaps: what exactly is returned, how 'run_id' scopes the artifacts, and what 'native files' means. There is no output schema to compensate, so the agent has to infer part of the contract.

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 never mentions 'run_id' or how it relates to the native files being indexed. The parameter is somewhat self-explanatory from its name, but the description adds no meaning beyond the 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?

The description states a specific action ('Index') on a resource ('native files') and adds a distinguishing behavioral note about not reading large TDR files into model context. It doesn't explicitly name sibling tools, but the second clause helps separate it from content-loading operations.

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 phrase 'does not read large TDR files into model context' implies this tool is appropriate when you want to index/listing without loading large content, but it does not explicitly say when to prefer it over alternatives such as read_log or list_experiments.

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