update_experiment

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

With no annotations, the description carries the full burden and does so: it discloses the monetary cost of changing a side, the replay/reuse/regrade lifecycle, that the previous scoring run is stopped, that the untouched side is left alone, and that preview mutates nothing and returns reused_sessions and replays_needed. This is well beyond what a bare mutation description would provide.

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 impact and cost warning is front-loaded, followed by mechanics, then the required preview workflow, then param glosses. It is dense but every sentence earns its place; the only noise is the retained docstring artifacts (':param', ':returns') and some repetition of the pipeline name/version phrasing.

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?

No output schema exists, yet the description explains what is returned (updated Experiment, the plan under preview, or an error message). No annotations exist, yet side effects, cost, and restart semantics are covered, so nothing material is missing for an agent to invoke this correctly.

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%, and the description compensates by glossing all eight parameters, adding real meaning for the non-obvious ones (recorded_baseline means the Dataset's recorded Sessions with nothing replayed; preview returns the plan; pipeline names must be paired with their version ids). It loses a point because the name/version pairing and any conflict/precedence rules between candidate and baseline fields are implied rather than specified.

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 set: 'Renames an Experiment or changes its candidate or baseline,' which is precise and immediately distinguishes it from get_experiment, create_experiment, and delete_experiment in the sibling list. An agent can tell what this does without opening the schema.

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 explicit workflow guidance: call with preview=True first, show plan to the user, get a yes, then change for real, and follow progress with get_experiment. It also clarifies cost conditions ('Only renaming costs nothing') and the instruction to send only what changes, which is exactly the when-and-how guidance an agent needs.

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