retry

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

With no annotations, the description carries the full burden of behavioral disclosure and delivers none. It does not explain retry policy, whether calls block until success or exhaust retries, what happens on final failure, or what side effects are repeated on each attempt.

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?

Two words is not conciseness but under-specification; there is nothing front-loaded because there is nothing substantive behind it. The brevity hides a complex, five-parameter tool.

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 tool with a nested object parameter, a required tool target, a success-check expression, and no annotations or output schema, the definition is completely inadequate. An agent cannot reliably invoke this tool without external knowledge of its contract.

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?

Five parameters (including a nested args object and a success_check expression) are documented at 0% schema coverage, and the description adds no meaning for any of them. The semantics of args, tool, delay_ms, max_retries, and success_check are entirely unexplained.

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?

"Automatic retry" is essentially a restatement of the tool name rather than a description of what the tool does. It does not say what is being retried (a tool call? a page action? a step?), what "automatic" implies for the caller, or how it differs from siblings like run_steps, batch, or reconnect.

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?

No when-to-use guidance, no conditions for choosing this over alternatives such as run_steps or batch, and no note about what kinds of operations are retryable. The agent is left to guess entirely from the name.

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