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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), and the description adds genuinely new operational facts: $0.08 USDC per call, prepaid credits accepted, and payment credentials must travel in X-Payment / X-Payment-Tx / Authorization headers rather than in arguments. That header requirement is exactly the kind of non-obvious behavior an agent needs before calling. It does not mention rate limits or response size, so it is not a 5.

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 points (full report, params, payment) are front-loaded, which is good. However, the payment and argument facts are restated three times across the English preamble, the [zh] block and the [en] block, and 'symbol 必填, quote 可选' is duplicated as '入参：symbol、quote' and 'Args: symbol, quote'. The bilingual duplication costs length without adding information.

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 does the work of explaining the return payload: per-source quotes, deviation in basis points from consensus, outlier flags, threshold definitions and coverage boundaries. Combined with the payment instructions, an agent knows what it pays and roughly what it gets. The remaining hole is the symbol/quote argument format.

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 description coverage is 0%, so the description must carry parameter meaning, but it only repeats that symbol is required and quote is optional — information already present in the schema's required list and property definitions. It never says what symbol format to use (ticker, pair, address?) or what quote selects (a currency, a default source, a comparison basis). Two parameters, one critical, remain semantically opaque.

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 names a specific resource and a specific output shape: 'full: every source quote, deviation from consensus, outlier flags', plus threshold definitions and why DEX quotes are excluded. An agent can tell this is the drill-down report rather than the top-line consensus number. It stops short of naming the sibling (price-consensus.consensus_price) that would complete the differentiation.

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 opening line 'Ask "what is the true price across sources"' frames an intent, and the word 'full' implies this is the detailed variant. But there is no explicit when-to-use versus when-not, and no statement that only one symbol may be requested per call at $0.08. Usage is implied rather than stated.

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