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

Annotations cover read-only/idempotent safety, but the description adds substantial behavior beyond them: it explains the classification outputs, the default liquidity floor, that thin pools signal wash/manipulation, that results are snapshots, and crucially the pricing model ($0.02/call, prepaid x-credit-token, 1 free call/day). These are meaningful operational details an agent needs. Does not describe return schema fields, but output schema exists.

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?

Front-loaded with the core question, but the body is dense and mixes classification semantics, pricing/billing details, a legal disclaimer, and payment mechanics in a single stream. Several sentences (especially the billing and disclaimer) could be trimmed or moved without losing invocation-relevant content.

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?

Covers what the tool does, the classification taxonomy, the liquidity floor, snapshot caveat, and payment/auth model. With an output schema present, not explaining return fields is acceptable. Only minor gaps remain around exact classification thresholds and which sibling to use for a live quote.

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%, so both parameters are already documented (address, minLiquidityUsd with default 5000). The description adds context on why minLiquidityUsd exists ('over a floor, default $5k') and that address is required, but nothing beyond the schema baseline.

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?

Opens with a specific question and verb+resource: comparing a token's price across Base DEXes. Clearly distinguishable from siblings like multi_price, token_price, pair_info, or wash_trading, since it explicitly frames itself as cross-DEX consistency analysis routing agents elsewhere for single-price lookups.

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?

Provides strong context on when the classification matters (arb window vs manipulation) and what each outcome means (tight, arb_window, wide, single_venue). Also cautions 'Snapshots — confirm with a live quote', implying follow-up with a live-quote sibling. Lacks explicit 'if you want X, use Y instead' routing to named alternatives, but the situational guidance is clear.

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