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

Annotations already cover readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds valuable details: 50-significant-digit precision (BigNumber), deterministic behavior, no AI or code execution, cost per call ($0.001 per x402), and that the result is an exact string. No contradiction.

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 four sentences, each adding significant value. It starts with a clear, engaging hook ('Exact math for agents'), then lists capabilities, usage example, and key traits. No extraneous words.

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 has one parameter, a clear schema, and an output schema (implied by 'result returned as an exact string'), the description fully covers what an agent needs: purpose, capabilities, precision, constraints, pricing, and deterministic nature. No gaps remain.

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 input schema has 100% coverage with a description. The description reinforces the format with examples and adds the constraint of max 400 characters. This goes slightly beyond the schema, earning a 4.

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 that the tool performs exact math, and lists specific operations (multiplication, division, roots, logs, etc.) and the use case (arithmetic LLMs get wrong). It differentiates itself from sibling math tools (like get_calc_dates, get_convert) by focusing on high-precision arithmetic.

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 when to use this tool: for arithmetic that LLMs are likely to get wrong. It doesn't explicitly exclude alternatives, but the context (50-digit precision, deterministic, no AI) strongly suggests using it for high-stakes math. A brief note on when not to use it would improve clarity.

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