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

With no annotations, the description carries the full burden and does: it defines terminal states ('approved'/'denied'/'pending'), warns to check proof_token, states that no link is returned, and discloses that polling is cut off client-side at the SDK's 60s default while server-side polling continues. It even calls out the auth prerequisite and that start_login does not unlock this tool.

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?

Purpose and backoff policy are front-loaded, and an explicit 'Agent usage:' block separates operational guidance from the mechanics. The sentence about get_confirmation_approval_link is dense, with two nested em-dash clauses, but every sentence carries decision-relevant content.

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?

There is no output schema and no annotations, yet the description covers return states, the proof_token to inspect, timeout semantics, and the authentication requirement. It stops short of enumerating the rest of the response payload, but the operational essentials are covered for a long-poll tool.

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 100%, so the baseline is 3: both parameters (id, timeout_seconds) are already documented in the schema, including the timeout's default/max and client-cutoff rationale. The description adds no parameter meaning beyond tying the id back to create_confirmation, which the schema itself already states.

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 confirmation until the approver responds') and immediately adds the polling mechanics (exponential backoff, 2s initial, 1.5x, 30s max, jitter). An agent can tell this apart from get_confirmation (one-shot read) and get_confirmation_approval_link (fetches a URL) without opening any 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?

Explicit sequencing: 'Call this after create_confirmation with the returned confirmation ID.' It names the alternative get_confirmation_approval_link and the exact conditions under which it is or isn't usable (still pending, before timeout_at), which is when-to-use guidance at its most concrete.

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