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

Annotations already declare destructive=true, openWorld=true, non-idempotent, and not read-only. Beyond those, the description adds genuinely new behavioral context: a confirmation gate requiring organizer approval, reuse of the web engine and current opt-out gates, no event required, and hard bounds on newsletter sampling (10–100% / 1–168h / minimum 100). Does not explain what activation destroys or how cancellation interacts with in-flight sends.

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?

Information-dense but crammed into two long multi-clause sentences that braid actions, parameters, constraints and preconditions together. It is front-loaded on the actions, which helps, but the newsletter-parameter clause interrupts the workflow and a reader must re-parse to extract the confirmation rule. Not padded, but not clean.

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 complex three-action mutation tool with no output schema, the description covers actions, required identity/verification inputs, confirmation gating, and points to a workflow guide resource. It omits what a successful response returns (per-action result fields) and whether cancel is recoverable, but the essentials for correct invocation are present.

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 67% and payload is an opaque nested object, so the description must compensate. It does: it enumerates the action enum values and the required identity fields (experimentId, definition, reviewHash, decisionHash, variant a/b) and spells out the newsletter definition vocabulary and its numeric constraints, which the schema does not.

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?

Names three concrete actions (activate, cancel, chooseWinner) on the email experiment resource, with the distinguishing hashes/fields each requires. An agent can identify the domain, but the description never names the sibling it replaces (e.g. inspect_email_experiment for reading, edit_email_review for editing), so differentiation rests on inference.

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 real when-to-use context: cancel by experimentId, chooseWinner only after an inconclusive newsletter test, and the preconditions (both variants shown, audience/allocation/timing/measurement presented before confirmation). No explicit when-NOT or named alternative tool, so it stops short of a 5.

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