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

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false, but leave the verification and fallback behavior undocumented. The description adds substantial context beyond annotations: it verifies the URL actually changed, falls back to the last FROM URL tracked internally, reports the path via 'via' ('history' or 'navigate'), and promises navigated:false with a 'reason' rather than a false positive. This is rich behavioral detail that structured fields do not provide.

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-loads the core action and then unpacks the iOS-specific fallback behavior. The description is dense and uses all caps for emphasis, but each sentence carries behavioral weight and avoids repetition of schema or annotations.

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, but the description thoroughly explains return fields (navigated, reason, via) and both the primary and fallback navigation paths. For a tool with tricky platform-specific history behavior, an agent has enough information 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%, with each of the four parameters documented in the schema itself. The description adds no parameter-level meaning, such as how pageId is auto-picked or when socket matters on Android, so the baseline of 3 is appropriate when the schema already does the heavy lifting.

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: 'Navigate the device browser back one entry in its session history (history.back())', with explicit platform scope for iOS Safari and Android Chrome. It is clear what the tool does, but it does not directly distinguish itself from sibling back tools such as web_back, session_back, or webpage_forward.

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?

Mentions the iOS case where history.back() may be accepted but ineffective right after ios_safari_navigate, which gives useful context for when the fallback applies. However, it provides no explicit when-to-use versus alternatives routing for sibling tools like web_back, session_back, or webpage_forward. Usage is implied rather than guided.

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