browser_find

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

It clearly discloses that the operation is a read-only search over the current page snapshot and that it returns refs for matches. It does not address edge cases like no snapshot or both parameters being supplied, but the core behavior is visible despite having no annotations.

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. Every phrase contributes information about the search target, match criteria, or return value.

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?

Basic invocation is clear: provide text or regexp and receive refs. However, with no required parameters stated and no guidance on what happens if both or neither are provided, an agent could make an ambiguous call.

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 100%, so the parameter descriptions already explain the text and regexp arguments. The description adds only that they are alternative match modes; it does not clarify exclusivity, precedence, or whether at least one is required.

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 names a specific action ('Search'), a resource ('current page snapshot'), and a result ('returning each match's ref'), and scopes the search to controls' name/value/role. This clearly distinguishes it from siblings like browser_snapshot and browser_evaluate.

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 description implies use when locating controls in the current snapshot by text or regexp, but it never states when not to use it or points to an alternative. It also omits prerequisites such as ensuring a snapshot exists.

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