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

Adds behavior the annotations cannot express: worst-case-across-the-set aggregation, feed outage surfaces as 'unknown' and never as healthy, per-call pricing ($0.01 over x402), prepaid x-credit-token header, 1 free call/day, and no wallet or API key required. This is exactly the extra context annotations don't carry.

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 and the measurement, then the risk rationale, then access/pricing terms. It is longer than necessary and contains a rhetorical hook and a 'Not financial advice' disclaimer, but nearly every sentence conveys usable operational detail.

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?

Output schema exists, so return values need not be specified, yet the description still outlines the shape (per-coin deviation in basis points plus healthy/watch/depeg status, worst-case across the set) and the outage edge case. Combined with annotations covering safety, nothing needed to call it correctly is missing.

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?

Only one parameter and schema coverage is already 100%, so the schema fully documents symbol and its default. The description's 'Pass symbol= for one coin' largely restates the schema rather than adding syntax, enum values, or format constraints, so the baseline of 3 applies.

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?

States a specific measurement (live DEX price vs the $1.00 peg) for a specific resource set (USD-pegged stablecoins USDC/USDT/DAI/USDbC on Base). It is clearly separable from siblings like b20_peg, b20_stablecoin, token_price, and price_alert, which name different chains or different output concepts.

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?

Gives concrete trigger context — an agent parked in stables reprices everything off a stale $1, and a depeg is silent because balanceOf doesn't change. It also explains the single-coin scoping knob ('Pass symbol= for one coin'). It does not name an explicit alternative tool or when-not-to-use, so it stops short of a 5.

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