browser_macro

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

Beyond the sparse annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description discloses that secrets are never written to the macro and are stored as {{secret}} placeholders, that omitting them 'fails visibly rather than leaking', and that replay refuses to act on weak or ambiguous matches. These are meaningful safety and failure-mode disclosures the annotations do not provide.

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 front-loads the core purpose and then organizes into action definitions, secret handling, and replay semantics. It runs long, but each sentence adds information, and the secret-handling and weak-match-refusal passages earn their length given their safety importance.

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 7-parameter, multi-action tool, the description explains the essential usage contract: actions, placeholder mechanics, and the safety/ambiguity rules. An output schema exists to cover return values, so the main remaining gap is that several parameters (goal, session, start_url, threshold) are left to an input schema with 0% prose coverage.

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. It richly documents `action` (five values with their effects), `name` (save/replay target), and `params` (placeholder substitution including the {{secret}} case). It leaves `goal`, `session`, `start_url`, and `threshold` unexplained, though the weak-match refusal partially hints at threshold semantics.

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 opening line 'Record, replay, list, or delete a macro — a discovered path with no model calls' gives specific verbs, a resource, and a defining trait. The 'no model calls' framing distinguishes this from sibling tools like browser_act and browser_observe, which drive live model-mediated interactions.

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 per-action context: record_start 'needs the session to be driving the task', run replays a name with params filling placeholders, and list/inspect/delete are enumerated. It doesn't explicitly name sibling alternatives or state when-not-to-use, but 'a discovered path with no model calls' implies the use case that separates this from live-action tools.

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