list_runs

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

With no annotations, the description carries the full disclosure burden, and it does so thoroughly. It reveals the exact response shape, ordering (pinned-first, newest-first), the non-obvious page-local meaning of `count`, and the missing optimizer objective caveat. It also documents API clamping on limit, which is exactly the kind of behavioral detail an agent needs.

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 long but every section earns its place: Returns, Ordering, CAVEATS, alternative tool routing, and Args. The one-sentence purpose is front-loaded, and the caveats are truncated to the two genuinely non-obvious behaviors rather than enumerated exhaustively. Structure with labeled sections makes it easy to scan.

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?

Given there is no output schema and no annotations, the description is essentially complete on its own. It defines the top-level return object, run summary fields including key_metrics examples, nullable key behavior, ordering, paging semantics, and caveats that would otherwise cause incorrect agent behavior. The only minor omissions (e.g., status enum values) are not necessary for successfully calling and interpreting this tool.

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%, so the description must fully compensate; it does. Each parameter is given meaningful semantics: artifact values with run id prefixes, model_hash purpose, limit page size with API clamp and default, and offset as rows to skip for paging. This far exceeds the bare type/title information in 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 opens with a specific verb and resource: 'List a model's saved optimizer or scenario run history.' It also distinguishes itself from sibling tools by explicitly pointing to get_optimizer_results/get_scenario_results for fetching full run details. The artifact types ('optimizer' vs 'scenario') further clarify scope.

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?

Usage guidance is explicit: use this tool to list run summaries, and use get_optimizer_results / get_scenario_results with a run_id when full inputs and results are needed. It also names update_run / set_run_pinned for curation and warns to page until a short page, which is actionable routing to alternatives.

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