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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuine context beyond them: the shape of what comes back and the important caveat that titles are untrusted web content, which affects how an agent should treat the output. Minor gap: no mention of behavior when no browser session is active.

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?

Two short sentences, the core action front-loaded and the security caveat in the trailing clause. No filler and nothing redundant.

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?

A single-parameter read tool with annotations and full schema coverage; the description additionally documents the return fields since there is no output schema. Nearly complete, with only the missing preconditions/error behavior keeping it below 5.

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?

Only one parameter, 'session', and the schema documents it fully at 100% coverage (including the 'Session from open_app' hint). The description adds nothing about it, so the baseline 3 for high schema coverage 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 ('List the phone browser's tabs') and enumerates the returned fields (index, url, title, active), so the agent can tell it apart from browser_snapshot or browser_open. It stops short of explicitly naming a sibling it is not, which keeps it from a 5.

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?

Usage is only implied by the resource name — there is no statement of when to use this rather than browser_snapshot or browser_screenshot, and no prerequisite such as requiring an app/browser to be open first. An agent can infer the intent but must guess at alternatives.

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