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

Annotations only declare readOnlyHint=true, but the description adds real behavioral context beyond that: the exponential-backoff schedule (2s/1.5x/30s max with jitter), the four possible outcomes, and the non-obvious side effect that a 'verified' session persists for the connection and signs a wide range of the caller's account records. That last point materially changes how an agent should treat the session.

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 purpose, then usage, then the reply-text caveat — a sensible ordering. The parenthetical enumerating everything the session signs (emails, phones, domains, API keys, 2FA, DNS credentials, verification requests, profile username and proof list) is long, but it does convey the blast radius of the credential, so it mostly earns its space.

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?

No output schema exists, and the description fully compensates by naming every return state ('verified', 'failed', 'expired', 'pending') and what each means for the caller. Combined with the retry guidance and the UX reminder, an agent has everything needed to drive the poll loop 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 description coverage is 100% — both `id` and `timeout_seconds` are documented in the schema, including the client-timeout caveat. The description reinforces the retry loop ('call this tool again with the same id') and implies the timeout/pending relationship, but adds no syntax or format detail the schema lacks. Baseline 3 applies.

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 specific verb and resource — 'Poll a login session until the user completes authentication' — and ties itself to start_login, which distinguishes it from the crowded wait_for_* family (wait_for_2fa, wait_for_session, wait_for_confirmation). An agent can pick this tool without opening the schema.

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 an explicit precondition ('Call this after start_login with the returned session ID'), enumerates terminal states, and prescribes the exact recovery path for the non-terminal case ('status "pending" ... call this tool again with the same id'). The pre-call reminder about surfacing the link in reply text is actionable guidance, not filler.

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