browser_read_control

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

With no annotations the description carries the full burden and does substantial work: it discloses that DOM and AX values are reported separately (i.e., non-atomic), that refs are bounded to preserve an existing snapshot, and it explicitly disclaims library-specific inference, complete virtual lists, application commit and atomic DOM/AX views. It stops short of stating read-only safety, permissions, or error behavior, but the limitation disclosure is genuinely informative.

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?

Front-loaded with the core verb and resource, and most clauses carry information. However, the trailing negation string ('No library-specific inference, complete virtual list, application commit or atomic DOM/AX view') is a compressed list whose meaning is hard to parse and partly ambiguous, costing clarity for brevity.

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 12-parameter tool with nested frame objects and no output schema, the description does explain the shape of what comes back (DOM/AX values, text, state, popups, options), which is necessary. But with no annotations and only 58% schema coverage, the remaining parameters and any error/timeout semantics go unaddressed.

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 58%, so several parameters (ref, tab_handle, max_chars, timeout_ms, frame_id) are undocumented in either place. The description only obliquely maps to parameters — 'bounded refs' to ref, 'currently exposed options' to max_options, 'related popups' to popup_selector, 'AX order' to nth — so it adds marginal semantics rather than compensating for the gap.

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+resource ('Read one explicit control') and enumerates what is returned: native DOM/AX values, rendered text, state, related popups, active descendant and exposed options. The closing clause implicitly contrasts it with broader reads (full snapshots, atomic DOM/AX views), so it is distinguishable from siblings, though the AX/DOM jargon makes the scope harder to grasp than it needs to be.

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?

'Bounded refs preserve the existing snapshot' hints at when this is preferable to a full snapshot, and the negation list implies when not to rely on it. But no sibling is named (browser_snapshot, browser_read_text) and there is no explicit 'use this when…' statement, leaving routing to inference.

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