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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds real value beyond that: it discloses what review returns (exact audience, immutable content, approval hash) and warns the agent to separate observed conversions/uncertainty from causal lift, a meaningful analytical caveat.

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?

Four tight sentences, front-loaded with the operation list before the return-value and caveat details. The parenthetical '(definition)' / '(experimentId)' phrasing is slightly clipped but efficient rather than wasteful.

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?

With no output schema, the description carries the return-value burden and does describe review's output plus an analytical caveat; the guide resource covers workflow depth. It is thinner on what list and report return and on the nested payload's other fields, but overall complete enough to call 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 only 50% and the payload is an opaque nested object, so the description must compensate. It does so by tying each enum action to its required payload key (definition for review, experimentId for report), which is more than the schema's generic 'IDs, expectedRevision, draft/definition, cursor, reviewHash' note provides for the action-parameter relationship.

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?

The description names the resource (email experiments shared with the web studio) and the three specific operations (list, review, report), so an agent knows exactly what it does. It does not explicitly name a sibling like start_email_experiment or edit_email_review, so differentiation is only implicit.

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?

It maps each action to its distinguishing input (review needs a definition, report needs an experimentId) and points to a workflow guide resource, which gives clear context for choosing a mode. It stops short of stating when NOT to use this tool or naming alternative siblings.

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