read_page

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

With no annotations, the description carries the disclosure burden. It discloses a key behavioral trait: the tool produces a snapshot with stable ref_N ids that remain usable for later targeting. It implies a read-only, non-destructive operation, though it does not explicitly discuss side effects, performance, or scope limitations.

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, front-loaded sentence with no filler. It leads with the core action and then gives the key use case, which makes it easy to parse quickly.

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?

The description gives the essential contract—the page snapshot contains stable refs for targeting—but does not describe the returned snapshot shape or how filter/max_refs affect the result. With no output schema and no annotations, this leaves gaps for non-default invocations, though the default call is reasonably clear.

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%, so the description must compensate for parameter meaning, but it does not explain filter or max_refs. The reference to click/type targeting only weakly implies the 'interactive' filter, and the agent must infer parameter semantics from names and enum values alone.

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 states a specific action ('Build an accessibility snapshot of the page') and a distinguishing outcome ('stable ref_N ids for click/type targeting'). This clearly differentiates read_page from siblings like get_page_content, list_elements, and inspect_dom, which focus on content or DOM structure rather than reference-stable accessibility snapshots.

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 'for click/type targeting' provides clear context: this tool should be used to obtain refs before performing click or type actions. It does not explicitly name alternative tools or state when not to use it, but the intended usage is reasonably clear.

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