retry_operation

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

No annotations are provided, so the description carries full burden. It mentions exponential backoff but lacks details on behavior after all retries, success/failure outcomes, synchronicity, or side effects. Overall, it offers minimal behavioral context.

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 concise sentences with no redundancy. The first sentence states the core function, and the second provides use context. All content earns its place.

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?

Without an output schema, the description should cover more behavioral aspects. It explains purpose and when but omits details like retry delay formula, return format, and error handling. This is adequate but not complete for a tool with 6 parameters and no annotations.

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 description adds no information about parameters beyond what the input schema provides. With 67% schema description coverage, the description should supplement missing parameter descriptions for max_retries and initial_delay_ms, but it does not, leaving gaps.

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 defines the tool's purpose: retrying operations with exponential backoff for temporary failures. It includes examples of use cases (API calls, network requests), making it specific and not a tautology.

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 provides guidance on when to use ('operations that might fail temporarily'), implying not for permanent failures. However, it does not explicitly state when not to use or suggest alternatives among sibling tools like cache_* or rate_limit_check.

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