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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavior beyond them: a daily per-caller quota on the free tier, the truncation to 5 results with only id/symbol/name, and the non-obvious auth mechanics (payment headers X-Payment / X-Payment-Tx / Bearer fg_… travel in MCP headers, not arguments). That payment-header instruction is genuinely useful and not inferable from any structured field.

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 core facts are front-loaded, but the text is padded with a duplicated English/Chinese restatement and vendor/payment boilerplate that is not specific to this tool. The opening "Ask 'what are the top coins by market cap'" hook occupies prime space yet describes an intent this tool only partially serves.

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?

There is no output schema, so the description usefully specifies the return shape (top 5, id/symbol/name, no quotes). With one optional-free parameter, no nested objects, and annotations covering safety, an agent has nearly everything needed to call it. The only shortfall is the underspecified matching behavior of q.

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 0% — the single parameter is documented only as "Q" of type string. The description compensates partly by identifying it as a name keyword (入参：q), but it never says whether a symbol or numeric id also works, whether matching is substring/prefix, or case sensitivity. For a 1-parameter search tool that is a real but not fatal gap.

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 English half states a concrete verb and resource: "locate a coin by name keyword" returning "id and symbol only", and the Chinese half pins the payload down further to the top 5 id/symbol/name with no market values. That is enough for an agent to distinguish it from a price-quote tool. The leading hook "Ask 'what are the top coins by market cap'" is a slightly awkward framing for a keyword lookup, which keeps it off a 5.

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 explicitly routes price/market data elsewhere: "行情数值走 top100_full", naming the sibling alternative and the condition that selects it. It also marks this tier as free, which is a usage-relevant constraint. It stops short of stating when *not* to use a keyword search at all (e.g., when you already have an exact id).

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