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

With no annotations provided, the description carries the full behavioral burden. It discloses that only visible elements are shown by default, that state (disabled/checked/expanded) and current field values are marked, and that refs survive markup shifts and reach elements selectors cannot. These are meaningful behavioral details beyond a generic 'read page' statement, though it doesn't mention performance, rate limits, or explicit read-only semantics.

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?

The description is a single dense paragraph that front-loads the core purpose and then layers usage, output format, benefits, and options. Every sentence contributes distinct information with no filler. It is longer than minimal but justifiably so given the complexity; the structure is logical and scannable.

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?

Given 8 parameters and no output schema, the description covers the critical aspects: what the tree looks like, how refs are used, default visibility, state markers, and configuration options. Parameters like limit, pageId, socket, and platformVersion are left to the schema, which fully documents them. The description is sufficient for an agent to call the tool 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 coverage is 100%, so the baseline is 3. The description adds semantic value by explaining the purpose of interactiveOnly ('just the things you can act on') and selector ('to scope it to one region of a large page'), and clarifies the default visible-only behavior that maps to includeHidden. This goes beyond the schema's bare parameter descriptions, earning a 4.

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?

The description opens with a specific verb and resource: 'Read the page as a structured tree.' It clearly explains the output format (role 'name' [ref=eN]) and how the refs feed into sibling tools, making the tool's role unmistakable even among a large sibling set. It also states cross-platform support (iOS Safari and Android Chrome), distinguishing it from generic web snapshot tools.

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?

The phrase 'START HERE before acting' is a strong, explicit usage directive that tells the agent when to invoke this tool. It also advises passing interactiveOnly:true for actionable elements and using a selector to scope to a region. However, it does not explicitly name alternatives or state when NOT to use it, relying on the 'START HERE' implication to cover exclusion.

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