browser_macro

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

Beyond the annotations, the description adds meaningful behavioral details: replay re-resolves each step by role and name, refuses to act on weak/ambiguous matches, and macros contain no model calls. There is no contradiction with the annotations' readOnlyHint=false and destructiveHint=false.

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 and front-loaded with a one-line summary followed by an action-oriented reference list. Every line earns its place, and there is no redundant prose or restating of schema fields.

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?

The output schema exists, so return values need not be described, but the tool is polymorphic with five actions and seven parameters. The description does not specify parameter requirements per action, what delete or inspect do in detail, or how threshold and start_url affect replay, leaving gaps for an agent invoking it.

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 description coverage is 0%, so the description carries the burden of explaining parameters. It does clarify action, name, params, and session indirectly, but threshold, start_url, and goal are left unexplained, and it is unclear which parameters apply to which actions beyond run/record_stop.

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 opens with a specific verb-and-resource statement: 'Record, replay, list, or delete a macro — a discovered path with no model calls.' This clearly distinguishes browser_macro from the other browser_* siblings, which focus on opening, observing, acting, or asserting, not on managing reusable discovered paths.

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 gives action-level guidance, including a prerequisite for record_start ('needs the session to be driving the task') and explains when to use run. However, it does not explicitly say when to choose browser_macro over related tools like browser_act or browser_observe, leaving some usage inference to the agent.

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