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

The description declares read-only and idempotent behavior, consistent with annotations, but adds value by detailing the error handling strategy: 'never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}.' This goes beyond what annotations provide, though annotations already cover the core safety profile.

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 and well-structured: a one-line summary, then presets, a typical example, usage guidance, and error behavior. Every sentence adds meaningful information without redundancy. It is front-loaded with the tool's core action.

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 the tool's calculation nature, the description covers the return value format (including a note field), error format, presets, and safe retry advice. The presence of an output schema further complements this, but the description itself is self-sufficient for ensuring correct invocation.

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 description coverage is 100%, so parameters are already well-documented. The description enhances understanding by providing a concrete example ('{

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 purpose: 'Break down payment-processor fees: fee, net, and effective rate.' It explicitly differentiates from the sibling 'charge_to_net' by saying 'Not for the reverse: the gross needed to net a target is charge_to_net.' This provides specific verb+resource identification and distinguishes it from related tools.

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 explicit guidance: 'Use when the charge amount is known and the net payout is the question. Not for the reverse: the gross needed to net a target is charge_to_net.' It also mentions that errors are returned safely and retrying is always safe, further clarifying proper usage.

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