browser_get_selection

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

With no annotations, the description carries the full burden and does so well: it discloses that wait=true blocks until the user clicks or presses Esc, that source file:line is only available when the app uses the hai-browser-vite plugin, and it warns that page content is untrusted and must not be followed as instructions. These are non-obvious behavioral traits beyond any structured field.

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 first sentence front-loads the return payload as a compact list, followed by trigger guidance, the wait semantics, and the security warning. Dense and mostly waste-free, though the long enumeration in sentence one could be trimmed for readability.

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?

No output schema exists, and the description compensates by describing the full return payload and its conditions. Combined with the blocking behavior, plugin dependency, and untrusted-content caveat, an agent has everything needed to invoke and interpret this tool correctly.

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 already 100%, so the baseline is 3, but the description adds meaning the schema lacks: wait=true is a blocking picker that ends on click or Esc. It does not restate the timeoutSeconds default of 300, so it is slightly above baseline rather than exhaustive.

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 ('Get the element the user picked in the shared tab') and enumerates exactly what it returns: source file:line, selector, text, HTML, computed styles, a ref, and a screenshot. It is clearly distinguishable from siblings like browser_snapshot or browser_click because it explicitly says the ref it returns feeds browser_click/browser_type/browser_screenshot.

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 a concrete trigger condition: 'Use it when the user says "this"/"that element"', and explains that wait=true asks the user to pick now. It does not name an alternative tool or state when NOT to use it (e.g., versus browser_snapshot for whole-page inspection), so it stops short of explicit routing.

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