browser_observe

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

With no annotations, the description carries the full burden and does well: it discloses that refs are generation-scoped, that they remain valid for browser_act, that auth_state is page evidence rather than a run-stopping condition, and that diagnostics reports errors and failed requests since the previous result. It never explicitly states the operation is read-only or mentions cost/rate characteristics, leaving a small gap.

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 core return shape is front-loaded in the first sentence, followed by behavioral notes and then the routing advice, so an agent gets the essentials immediately. It is dense but every sentence carries information; a few clauses (auth_state, diagnostics) could be tightened without loss.

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?

There is no output schema, so the description must describe results, and it does: element refs, content_blocks, scroll_containers, auth_state, diagnostics, and the 'elements were not shown' signal. Combined with 80% schema coverage and one enum, the definition is nearly self-sufficient; only explicit read-only framing and pagination/volume expectations are missing.

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 80%, so the baseline is 3, but the description adds genuine meaning beyond the schema: query searches the whole page (not just the last observation), within scopes to a region, frame or element, and cursor continues the prior ordering. It frames these as one coherent narrowing strategy rather than restating field definitions, though it does not add format/syntax detail for within or cursor values.

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 verb and resource ('Observe a live tab') and enumerates exactly what is returned: generation-scoped element refs, on-screen controls first, content_blocks and scroll_containers. That level of specificity separates it cleanly from browser_evaluate, browser_extract and browser_screenshot without opening any schema.

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 gives explicit routing: 'When the result says elements were not shown, narrow the view instead of reading the DOM with browser_evaluate', and points to query/within/cursor as the narrowing path. It also tells the agent how to treat auth_state. It stops short of contrasting with the other siblings (browser_extract, browser_screenshot, browser_flow), so it is strong but not exhaustive.

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