Query browser

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

The description adds important context beyond the annotations by warning that some observations 'may activate a tab or attach debugger instrumentation.' This qualifies the 'read query' label and introduces realistic side effects, which is especially valuable given that readOnlyHint is false. The description does not contradict the annotations; it complements them.

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 two sentences with no wasted words. The primary purpose is stated first, followed by a concise caveat. Every word contributes to comprehension, and the length is appropriate for the tool's generic dispatching nature.

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?

Even though the schema describes the 'action' parameter as returned by browser_capabilities, the description omits crucial context: how to discover valid actions, what the output format is, how 'params' should be structured per action, and what side effects may be expected beyond the vague note. The tool is complex with nested targets and retry options, and no output schema exists, so the description is insufficient for an agent to invoke it effectively on its own.

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 description itself explains none of the eight parameters, despite schema description coverage being only 25%. It does not compensate for gaps around 'action,' 'engine,' 'target,' or retry fields一波. The only parameter explanation comes from the schema itself (for 'action' and 'engine'), so the description adds no value to parameter understanding.

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 states a specific action: 'Run a catalog-defined read query.' This clearly identifies the tool's purpose as executing predefined read operations and differentiates it from mutation or snapshot tools by emphasizing the read nature. However, it does not explicitly name a sibling tool or further clarify what distinguishes a 'query' from browser_capabilities or browser_action.

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 provides no guidance on when to use this tool versus alternatives like browser_action or browser_batch. It never mentions any condition that would select this tool over others, nor does it explain prerequisites such as calling browser_capabilities first to obtain valid actions. The 'catalog-defined' phrase hints at external definitions but leaves the decision entirely to inference.

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