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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds real context beyond them: it requires `write` scope, mutates flayr data, freezes the current round's numbers, and carries the best arms forward. It does not say what happens when no round is open or how the call behaves on repeat, which the non-idempotent annotation implies matters.

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?

Three tight sentences, front-loaded with the write-scope marker and the core action, followed by the recording rule and the user-confirmation requirement. Nothing is redundant.

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?

For a two-parameter mutation with no output schema, the description explains the effect on state but omits the identifier semantics, preconditions for the open round, and any indication of what the response returns. Adequate but with clear gaps.

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 carry the load. It explains `pick` well (an arm the user chose, confirm with the user first) but never clarifies `id` — whether it is the experiment id or the round id — which is the required parameter and a plausible source of mis-calls.

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 ('Freezes the open round's numbers and keeps the best arms for the next round') and names the upstream endpoint, so an agent can separate it from start_experiment_round and get_experiment_rounds 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 conditional guidance for the optional parameter: a winner is recorded only on likely_winner readout or an explicit `pick`, and the agent must ask the user first. It stops short of stating prerequisites such as 'a round must be open' or naming sibling alternatives.

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