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

Annotations only cover the safety profile (readOnly, idempotent, non-destructive); the description adds materially more: the hard privacy limitation that notification title/body cannot be returned, the default early-return behavior, and that no automation session is required. This is exactly the behavioral context annotations cannot express.

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 privacy limitation, then timing — a logical order. It runs long at roughly eight sentences, but each carries distinct information (limitation, fallback tool, default timing, session requirement), so little is wasted.

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 and six parameters, the description compensates by enumerating what is reported (which app, when, OTP presence, shown vs suppressed) and what is deliberately withheld (title/body). An agent has everything needed to call it correctly and interpret the result.

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 every parameter (seconds, bundleId, oneTimeCode, waitForFirst, oneTimeCodeOnly) is already documented. The description's mention of 'which app was notified' and 'whether the notification contained a one-time code' loosely maps to bundleId/oneTimeCode but adds no syntax or default detail beyond the schema, so 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 ('Watch which notifications an iOS device receives and return them') and immediately scopes it against the sibling ios_page_source for reading notification text. An agent can distinguish this from device_notifications, ios_syslog_capture, and ios_page_source without opening a 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 trigger scenario (confirming a push or OTP arrived after a login), timing instructions ('trigger the action first and call this straight after'), and names the alternative tool (ios_page_source) for the case where the text is needed. Both when-to-use and when-to-use-something-else are covered.

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