wait_for_session

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

Goes well past the readOnlyHint annotation: it discloses the polling strategy and backoff parameters (2 s initial, 1.5x, 30 s max, jitter), the timeout return semantics (status "pending"), and an auth prerequisite (PROOF_API_KEY must be set and the server restarted). That is exactly the operational context annotations cannot carry.

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 is front-loaded in the first sentence and the three paragraphs are cleanly separated (behavior, usage caution, access). Every sentence carries information, though the exact backoff constants are more detail than most callers need.

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?

With no output schema, the description compensates by naming the terminal states and the pending-on-timeout return value, and it flags the required credential. Minor gaps remain: it doesn't say what the session object looks like or how to distinguish which session type is expected.

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%, so both id and timeout_seconds are already fully documented in the schema, including the 60 s SDK client-timeout interaction. The description repeats the pending-on-timeout behavior but adds no new per-parameter meaning, so the 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 (poll/wait) plus resource (session) and enumerates the terminal states (verified, failed, expired), which tells an agent when the call resolves. However, it never distinguishes itself from the many sibling waiters (wait_for_verification, wait_for_login, wait_for_request, wait_for_2fa) or ties itself to create_session/get_session, so the agent must infer which 'session' this applies to.

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 a genuine precondition ('before calling this for a challenge you created, make sure your reply text already shows the user what to act on') and tells the agent to re-call with the same identifier on timeout. It gives no guidance on when to prefer this over the other wait_for_* siblings or when to skip polling in favor of a single get_session call, so selection guidance is only implied.

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