Advanced Rounding

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description is not burdened to cover safety. It adds value by detailing each method's rounding behavior (e.g., 'floor: Always round down (3.149 → 3.14)') and showing examples. This clarifies nuances beyond annotations, such as treatment of negative numbers in truncation.

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 well-structured with a clear header, method list, and examples. It starts with the purpose and quickly enumerates methods. However, the example section is somewhat repetitive (multiple examples showing similar patterns) and could be trimmed without loss of clarity, earning a 4 rather than 5.

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?

Given that an output schema exists (per context signals), the description is not required to detail return values. It covers all methods, parameters, and provides comprehensive examples. There are no obvious gaps for a rounding tool; edge cases like very large decimal places are not mentioned but are not critical for basic understanding.

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 100% with good descriptions for each parameter. The description adds significant value by providing concrete examples for each method and for multiple values, demonstrating the parameter combinations in action. This goes beyond the schema's static descriptions, helping the agent predict outputs.

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 it provides 'Advanced rounding operations with multiple methods' and lists four methods (round, floor, ceil, trunc) with explicit examples. This specific verb+resource combination, 'round' with 'Advanced Rounding' title, makes the tool's purpose unmistakable and distinguishes it from mathematical siblings like 'calculate' or 'percentage'.

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 implicitly guides when to use this tool (for rounding operations) but does not explicitly state when to use it versus alternatives like 'calculate' or 'percentage'. There is no mention of context or exclusions, so the agent must infer usage solely from the tool's name and method list.

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