zen_retry

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

No annotations are provided, so the description carries the full burden. It explains the exponential backoff mechanism, default behavior (retry on any error), and parameter details (max_attempts includes first try, backoff_ms doubles). It could add more context about idempotency or side effects, but the main behaviors are disclosed.

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 concise with a clear verb + resource statement followed by a parameter list. It is front-loaded and uses efficient formatting. The 'Args:' block could be slightly more compact, but overall it's well-structured.

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 4 parameters, no output schema, and no annotations, the description covers the input semantics well. However, it does not mention the return value or what happens on success/failure. Given that the tool wraps a command, the return likely mirrors the command's output, but explicit mention would improve completeness.

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?

The schema has 0% description coverage, but the description thoroughly explains each parameter: command is a dict like zen_batch entries, max_attempts is total tries, backoff_ms initial wait doubling each retry, and on_errors substrings to filter errors. This adds significant meaning beyond the schema's type and default 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 clearly states the tool's function: 'Wrap any command in exponential-backoff retry.' It specifies the command shape matches zen_batch entries, distinguishing it from sibling tools like zen_batch and others that execute commands but do not include retry logic.

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 implies usage for retrying commands with exponential backoff but does not explicitly state when not to use it or mention alternatives. It provides parameter details but lacks guidance on scenarios where retry is inappropriate.

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