get_evaluation_run

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

With no annotations, the description carries the full burden and does well: it defines the status/outcome state machine (ENDED + SUCCEEDED yields metrics, ERRORED means the evaluator code broke and points to error_detail, FAILED never completed and can be re-run). It also discloses that results are persisted to the object store and returned as a preview with an object ID, though permissions and read-only guarantees are unstated.

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 core behavior is front-loaded, but the text carries Sphinx-style ':param' and ':returns' markup and three separate sentences about object IDs and the object store, which repeat the same point. Trimming the duplicated storage/object-ID text would sharpen it.

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?

There is no output schema, so the description must convey return semantics, and it does: status, outcome, metrics, error_detail, and the object-store preview are all described. What remains missing is how run state is obtained if not ENDED (polling cadence, timeouts) — minor for a read 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 compensate. It explains the provenance of evaluation_run_id (from run_evaluator or list_evaluation_runs), which is genuinely useful, but pipeline_name is only glossed as 'Name of the pipeline' with no format or qualification guidance.

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 ('Reads one Evaluation Run') plus scope: current progress versus post-run findings. It also names the producing siblings (run_evaluator, list_evaluation_runs), so an agent can immediately tell this apart from the listing tool.

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 says to use it to follow a run that run_evaluator returned while still in progress, and where the evaluation_run_id comes from. It lacks an explicit exclusion (e.g., 'use list_evaluation_runs to enumerate runs instead'), which keeps it below a 5.

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