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

Annotations already cover read-only, idempotent, non-destructive, open-world behavior, so the description's added value is in the operational details: free tier with a daily per-caller quota, and the critical instruction that payment headers (X-Payment / X-Payment-Tx / Bearer fg_…) go in MCP request headers rather than parameters. That is genuinely useful context an agent cannot get from annotations.

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 answer (snapshot time, record count, no full records) is front-loaded, but the definition is bilingual and partially redundant, with the Chinese block restating what the English block already says. It is readable but roughly twice the length it needs to be.

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 must describe the return payload, and it does: snapshot/collection time, total record count, and a checksum summary. It also covers cost/quota and auth-header placement, leaving little an agent needs that 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?

The tool has zero parameters and the schema is empty, so the baseline is 4. The description confirms "入参：无" and reinforces that payment credentials must not be passed as arguments, which prevents a plausible misuse.

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 concrete resource and return shape: "Snapshot time and record count only" plus "免费返回采集时间、总记录数与校验摘要，不返回完整记录". It implicitly separates this from heavier siblings like ai-2.export by stating it does not return full records, though the sibling is never named.

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 phrase "Ask 'when was pricing refreshed'" gives one concrete scenario, and "不返回完整记录" implies the export/preview tools exist for full data. However, there is no explicit when-to-use / when-not-to-use guidance and no named alternative.

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