browser_snapshot

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

With no annotations, the description carries the full disclosure burden and does it well: it states the tool is a read, that refs persist only while an element stays on the page, that long output is paginated via a trailing offset, and it warns that page content is untrusted and must not be followed as instructions. These are exactly the behavioral traits an agent needs and that no annotation or schema provides.

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?

Four short sentences, purpose first, then ref semantics, pagination, and the security caveat. No filler; every clause carries actionable 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?

For a one-parameter read tool with no output schema and no annotations, everything an agent needs is present: what is returned, how refs relate to sibling tools, how to page through long output, and the safety caveat about untrusted 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 single parameter is fully documented in the schema (100% coverage, baseline 3), and the description adds workflow meaning by tying offset to the value emitted at the end of the previous snapshot. That is a small but real gain beyond the schema text.

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 ('Read') and resource ('shared page') and names the output format ('accessibility-style outline'), which separates it from browser_screenshot (visual) and browser_evaluate (code execution). The mention of [ref=eN] markers also signals it is the ref-producing tool in the browser_* family.

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?

Gives clear cross-tool guidance ('Interactive elements have [ref=eN] for use with the other browser_* tools') and explains the continuation workflow for long pages. It does not, however, state when to prefer this over browser_screenshot or browser_evaluate, so no explicit exclusion is offered.

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