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

Annotations already declare non-readonly, non-destructive, open-world, non-idempotent. The description adds materially: navigation is typed into the address bar and submitted, and success is verified via Web Inspector rather than assumed, which tells the agent about reliability and failure reporting. It does not describe failure modes or auth needs, so it is strong but not exhaustive.

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 the core action and mechanism before the routing advice. Dense but every clause carries information (mechanism, verification, alternative, precondition). Slightly packed with parentheses-emphasis, but no filler sentences.

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, so the description carries the return-behavior burden and does so by explaining that success is verified rather than falsely reported. Combined with full param coverage and the session precondition, an agent has enough to invoke it correctly; only error/failure details are 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 100% (url and udid both documented, including the 'include https://' hint). The description adds no syntax or format detail beyond the schema, 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 (navigate) and resource (Safari URL on iOS device) plus the mechanism (address-bar type + submit) and the verification step. It explicitly distinguishes itself from ios_safari_navigate, which an agent can compare against without opening either 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 routing rule: 'For Safari, prefer ios_safari_navigate (CDP-based, also cold-opens Safari)', and states the precondition that an active iOS automation session is required but auto-starts. When-to-use and the alternative are both named.

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