rescore_experiment

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

With no annotations supplied, the description carries the full burden and does so: it warns that the call costs money and that every evaluation is billed again, clarifies that sessions are not replayed (so no new execution data appears), and reports that hub-api returns an error message while a side runs or when nothing has been scored. That is exactly the cost/irreversibility/error surface an agent needs before invoking a paid mutation.

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?

Front-loaded correctly: the action and the cost warning appear in the first two sentences, with preconditions and follow-ups after. The trailing ':param'/':returns' docstring fragments are slightly mechanical, but every sentence still carries information an agent needs.

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, and the description explicitly closes that gap ("The Experiment, or an error message"), while also covering preconditions, cost implications, and next-step tools. For a one-parameter paid mutation, nothing material needed to call it correctly is missing.

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?

The single parameter has no schema description (0% coverage), and the description supplies only "The Experiment's id." — which identifies the field but adds no format, sourcing, or lookup guidance (e.g. how to obtain the id). Given the parameter is a plain required identifier whose meaning is largely self-evident, this is close to adequate but not fully compensating for the coverage gap.

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 ("Scores both sides of an Experiment again") plus the scoping condition ("with the Metric Group as it is now"). It implicitly separates itself from session-replay siblings by saying "the Sessions are not replayed" and from update tools by naming update_metric_group/update_evaluator as prerequisites rather than alternatives.

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?

Gives an explicit trigger ("Use it after changing the Metric Group's Evaluators or weights"), names the two tools that create that situation, and states the refusal conditions (a side still running, or no side scored). It also names the follow-up chain get_experiment then get_experiment_results, so the agent knows what to do before and after.

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