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

The description says 'Pure Read-Only' while the annotations declare readOnlyHint=false, and it claims 'zero external API calls' while openWorldHint=true. These are direct contradictions of structured behavioral metadata, so the description cannot be trusted for operational safety 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?

The definition is a single dense sentence that front-loads payment context and then states the computation. It is efficient, though the long run-on structure and redundant read-only framing keep it from being maximally clean.

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?

With no output schema, the description usefully names the computed outputs, and the fully covered input schema handles parameter details. But the payment/auth context is only briefly stated and the annotation contradictions leave the agent with an incomplete or inconsistent behavioral picture.

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%, and the schema already documents shares, taker_fee_bps, and outcome_ask_prices with defaults and an example. The description adds conceptual context that prices are caller-supplied mutually exclusive outcomes, but it does not add format or semantic detail beyond the schema.

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 gives a specific verb and resource: it computes NegRisk/Dutch-book probability sum, overround/underround in bps, fee drag, and net edge from supplied outcome prices. This clearly distinguishes it from sibling calculation and audit tools without needing the schema.

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?

It states the operating context—caller-supplied prices, zero external API calls, and zero order routing—which implies it is for offline math auditing rather than execution. However, it does not explicitly name when to use it instead of alternatives such as amm_constant_product_calc or the DeFi execution-risk tools.

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