browser_observe

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

With no annotations, the description carries the full burden. It discloses the behavioral output of each level (status, elements, screenshot), but does not explicitly state that observation is non-destructive. However, the term 'observation' and the nature of the levels strongly imply read-only behavior, so it is adequately transparent.

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 compact—two sentences—and front-loads the core principle ('use the cheapest level that suffices') before listing options. Every sentence adds value without redundancy.

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 single-parameter tool with no output schema, the description is complete. It covers what each level returns, how to choose, and how it relates to siblings. No essential information is missing for correct invocation.

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 schema only defines 'level' as a number with no description (0% coverage). The description compensates fully by explaining the meaning of levels 0, 1, and 2, including token counts and equivalences. This gives the agent complete information to select the correct value.

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 clearly states it is a 'layered observation' tool and explains each level's purpose, explicitly referencing sibling tools (browser_elements, browser_mark_screenshot) to differentiate. This distinguishes it from the many other browser tools.

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?

It explicitly instructs to 'use the cheapest level that suffices' and describes what each level provides, giving direct guidance on when to choose which level. It also names the sibling tools that match higher levels, making selection unambiguous.

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