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

Annotations only declare the generic mutation profile (not read-only, not destructive, not idempotent, closed-world); the description adds real value beyond that: `write` scope requirement, that entries land in an approval queue rather than going live, spaced scheduling slots with UTM links, and the round-2 semantics. It stops short of describing error behavior, what happens if the same round is started twice (relevant given idempotentHint=false), or the response.

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 with the scope/effect marker, then consequences, then round semantics; every sentence carries information. The trailing endpoint parenthetical is mildly redundant but useful for debugging, and nothing is padded.

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 3-parameter mutation with no output schema, the description covers the important unknowns: side effects (approval queue, not publication), auth scope, and round semantics. The remaining gaps — identifier meaning, valid platform values, and return value — are the reason this isn't a 5.

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 only 33% — only `startAt` is documented — so the description has to carry weight. It clarifies that slot spacing and UTM links are applied automatically (explaining the absence of such parameters), but never states that `id` is the experiment identifier or what values `platforms` accepts (a free-form string array capped at 10 with no enum).

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 concrete verb and effect — filing the round's versions into the approval queue on the given platforms — rather than restating the name. It also distinguishes the outcome from the sibling `publish` tool by noting that nothing posts until a person approves, so an agent can tell the two apart without opening schemas.

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?

The description implies when this is used (round 1 setup vs. round 2 re-testing kept arms) and names the precondition that approval is required downstream. It gives no explicit guidance on alternatives such as `create_experiment`, `close_experiment_round`, or `publish`, and doesn't state what experiment state is required before starting a round.

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