Read the page structure

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint, so "Changes nothing" is largely redundant. The description does add two pieces of genuinely new context an agent needs: password-like field values are masked in the output, and page text must be treated as untrusted (a prompt-injection warning).

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?

Three compact sentences, front-loaded with the return format, followed by the two caveats. No filler, and every clause (output shape, selector hints, masking, untrusted text, read-only) carries information.

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, the description correctly supplies the return format and safety caveats, which is the bulk of what matters for a read tool. However, it omits both parameters and any truncation behavior tied to maxNodes, leaving a gap for a 2-parameter tool with 0% schema coverage.

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 0% and the description never mentions profileId (required, identifies which profile/tab) or maxNodes (20-1000). An agent gets no guidance on what maxNodes does, its default, or whether exceeding it truncates the tree, so it must rely on the bare parameter names and the min/max constraints in the schema.

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 ("Returns the main tab's accessibility tree") plus the exact shape of what comes back: short lines of role, name, state, with {aria/Name[role="..."]} selector hints for interactive elements. That format implicitly separates it from page_extract_text and page_screenshot, but no sibling is named, so the differentiation is inferential rather than explicit.

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: the mention of selector hints "for elements you can click or type into" suggests calling this before page_click or page_type, but the description never says when to prefer it over page_extract_text or page_screenshot, and mentions no prerequisites such as a started profile or loaded page.

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