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

With annotations already declaring destructiveHint=true and idempotentHint=false, the description still adds substantial context the structured fields cannot: it states the tool is mutating, that `idempotency_key` is required, that the same key within 30s returns a cached response while a fresh key runs a new pass, and that `create_login_link` is refused on a non-main server. This is exactly the kind of side-effect, caching, and refusal behavior an agent needs before invoking.

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?

The core action and the mutating/idempotency warning are front-loaded, then status interpretation is organized into terse bulleted groups, which suits the high branching complexity. It is long, and lines like the `data.set_events_seen` nuance sit near the edge of what earns its place, but the structure keeps it navigable.

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 high-complexity, many-state tool with an output schema present, the description supplies the missing behavioral and routing context (state meanings, follow-up tools, multi-server handling). Because a return schema exists, its detailed restatement of `status`/`scoring_complete`/`retry` fields is partly redundant, but nothing essential is absent.

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 only 25%, so the description must compensate, and it does for the most important parameter: it explains that `idempotency_key` is required and defines its 30-second caching semantics. However it says nothing about `expected_domain`, `expected_events`, `onboarding_session_id`, `auth_token`, or `container_hash`, leaving most parameters documented only by pattern/type.

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 opening sentence states a specific, multi-part action: force-process recent events, recalculate scoring, and return a verification diagnosis. That clearly separates it from list/get siblings like get_status or get_summary, though it never explicitly names what it is NOT, so an agent must infer the boundary from behavior rather than an explicit contrast.

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 gives strong conditional routing: it tells the agent what each `not_ready_reason` means and what to do after the retry budget is exhausted (`get_next_steps` + `create_login_link`). It stops short of an explicit 'call this when...' statement or an exclusion against similar verification/status siblings, so context is clear but not exhaustive.

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