browser_retry

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

With no annotations, the description must carry behavioral load. It explains backoff doubling, max_attempts total tries, and error-substring filtering, but omits failure/return behavior and any warning about retrying non-idempotent commands.

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?

One-line summary followed by a compact Args block; every line adds information and the purpose is front-loaded.

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?

Covers retry mechanics and parameters, but with no output schema and no annotations it leaves return values and failure semantics unstated, and does not warn about side-effecting commands. Adequate but incomplete for a wrapper tool.

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 0%, so the description must compensate; it defines each parameter: command via reference to browser_batch entries, max_attempts, backoff_ms, and on_errors default. The nested command shape remains only cross-referenced rather than fully specified, but this is effective given the schema.

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?

Names a specific operation, wrapping commands in exponential-backoff retry, and ties the command shape to sibling browser_batch entries. It does not explicitly contrast with browser_batch or other alternatives, but the purpose is unambiguous.

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?

Provides conditional retry guidance via on_errors and implies use for flaky commands, but never states when to choose this over browser_batch, browser_parallel, or plain execution, nor when not to retry.

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