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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description layers on specifics they cannot: delete_account removes 'the account and all its data', clear_personalization is a distinct destructive branch, the confirmation requirement is mandatory, and trip-scoped locations 'never replace home'. That is meaningful behavioral context beyond the structured hints.

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 core verb pair, which is good, but the body is a single comma-chained run-on enumerating nine concepts with the two destructive caveats buried in a trailing parenthetical. Given the tool's breadth the length is defensible, yet the flat list makes the high-risk branches hard to scan.

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 12-parameter, 8-action, destructive-capable tool with no output schema, the description covers the preference surface acceptably but omits the action-to-parameter contract and says nothing about what the 'get' action returns. An agent knows the vocabulary of the tool but not how to compose a correct call for most actions.

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% across 12 parameters and 8 enum actions, and the description lists domain concepts rather than mapping them to parameters or actions (e.g. weight, max_price, currency, radius_km, is_default, location_label are never addressed, and no action-to-parameter pairing is given). It does add real semantics for valid_from/valid_until scope behavior, but that is one nugget against a wide undocumented surface.

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 gives a clear verb pair and resource ('View or change the user's event preferences and privacy') and enumerates the domain of mutable state (budget, days/times, timezone, interests, saved locations). It is distinguishable from siblings like manage_event_watchlist or track_event_interests, though it never names an alternative to route against.

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 states a genuine precondition for the most dangerous paths — clear_personalization and delete_account 'both need confirm: true and an explicit request from the user' — which is real usage guidance. However, it gives no when-to-use-vs-sibling routing (interests here vs. track_event_interests, watchlist vs. manage_event_watchlist), so the agent must infer which tool owns interest tracking.

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