Snapshot editor state

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds value by disclosing the shape of what comes back (URL, title, role + accessible name per element) and its relative cost. It stops short of noting limits such as off-screen, iframe, or shadow-DOM content being excluded, or any truncation on large pages, which would matter for an openWorldHint tool.

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 sentences: the first front-loads what is returned, the second front-loads when to use it and the cheaper-than-screenshot tradeoff. No preamble, no repetition of the title, and every clause carries distinct 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 carries the burden of describing return values and does so adequately by listing the fields and element attributes. The only gap is that it says nothing about scope boundaries of "visible" content or snapshot size, which an agent may need when a page renders large or nested content.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline applies. It correctly implies the snapshot targets the current page state with no filtering arguments, matching the empty 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?

"Return a compact text snapshot of the current page" names a specific verb and resource, then enumerates the payload (URL, title, visible buttons/links/textboxes/headings with role + accessible name). That enumeration cleanly separates it from gsites_screenshot (pixels) and gsites_get_text (prose extraction), so an agent can select it without opening any schema.

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?

"Use it to discover exact labels before gsites_click / gsites_type" gives an explicit trigger and names the two downstream siblings it feeds, which is exactly the routing information an agent needs. The closing cost comparison ("Cheaper than a screenshot") additionally resolves the obvious alternative-selection ambiguity against gsites_screenshot.

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