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

Annotations already cover readOnly/idempotent/openWorld/non-destructive, but the description adds substantial context beyond them: 5-minute caching, a low-liquidity flag, a defined 'unsupported-token error — never a fabricated price' behavior, and the full x402 payment flow where the caller's wallet pays and the server never does. This is exactly the behavioral disclosure the annotations do not 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?

The key facts are front-loaded ([PAID] tag, price source) and most sentences are load-bearing. There is mild redundancy — the '$0.003 USDC on Base via x402' cost and the 'your own wallet pays, never this server's' rule appear more than once — which costs it a point.

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 compensates by describing the return shape (leader-compatible prices[]/asOf/count/unresolved). It also covers caching, error behavior, and the payment handshake, so nothing an agent needs to invoke this 5-param, nested-object tool 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?

Schema coverage is 100%, so the schema documents every parameter including the payment_header nested shape. The description reinforces the batch nature of `coins` and its leader-compatible semantics, but adds little syntax or format detail beyond what the schema already states — the baseline 3 for full schema coverage.

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 states a specific verb and resource ('Base token price read live from on-chain state') and names the exact pricing sources (Chainlink Data Feed aggregators on Base, deepest Uniswap V3 USDC pool). An agent can tell this apart from gas_price, crypto_news, and the other siblings without opening 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 gives a clear calling workflow ('call with no payment_header first to receive the payment requirements' then retry with the signed header) and states the pricing path selected per input type. It does not explicitly name the free sibling token_price_preview as the alternative for no-payment use, which keeps this from a 5.

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