list_evaluation_runs

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

No annotations are supplied, so the description carries the burden. It does disclose valuable behavior: newest-first ordering, the absence of further paging, and that a result of exactly `limit` may be truncated — but it says nothing about permissions, error modes beyond 'an error message', or cost of large limits.

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?

Core purpose and the ordering/caveat details are front-loaded and earn their place, but the docstring-style ':param'/':returns' lines and the three-sentence object-store boilerplate add bulk that is generic across tools and dilutes the high-value content.

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?

With no annotations and no output schema, the description does useful work by enumerating returned fields (session_id, evaluator_version_id, outcome, metrics) and explaining the object-ID preview workflow. It still omits guidance on how to interpret `metrics`, what `outcome` values mean, or behavior on an unknown pipeline name.

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 coverage is 0%, so the description must compensate, and it does for `limit`: it states the 200 cap and the paging/truncation caveat, which is meaningfully beyond the bare integer schema. `pipeline_name` is only glossed as 'Name of the pipeline', which is close to tautological for the sole required parameter.

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?

States a specific verb and resource ('Lists a pipeline's Evaluation Runs'), adds ordering ('newest first'), and defines the unit of a run ('one Evaluator version judging one Session each'). It also scopes which runs are included (scoring-run cells, run_evaluator output) and names get_evaluation_run as the single-item counterpart, so an agent can distinguish it from list_experiment_runs and other list tools.

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?

Explicitly routes the agent to get_evaluation_run when it wants a single run, and clarifies which runs are covered. It lacks explicit when-not guidance versus adjacent listing tools (e.g. list_experiment_runs), which keeps it short of a 5.

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