dashai_list_runs

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds return format and filtering context, but does not disclose additional behavioral traits such as rate limits or auth needs. This is acceptable given the strong annotations, but not exemplary.

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 compact and well-organized: a clear purpose statement, a usage hint, a structured Args section, and a Returns section. Every sentence adds value, and the most important information (what it does) is front-loaded.

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 straightforward list tool, the description covers purpose, usage context, parameters, and return shape. It is complete enough for an agent to select and invoke the tool without needing external documentation, especially with strong annotations and a simple schema.

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?

Despite context showing 0% schema description coverage, the description explicitly explains both parameters: model_session_id as 'filter by experiment' and limit as 'maximum to return, 1-200 (default 50)'. This fully compensates for the schema gap and adds practical meaning beyond parameter names.

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 opens with 'Lists the recorded training runs, with their status,' which clearly states the action (list) and resource (training runs). It also distinguishes from siblings by focusing on training runs and comparing models within an experiment, avoiding confusion with list_datasets or get_run.

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 'Useful for comparing models trained within the same experiment' provides a clear context for when to use this tool. It implies usage for browsing runs and filtering by experiment, but does not explicitly exclude alternatives like get_run for single-run details, so it misses the top score.

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