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

The description frames the operation as pure data fetching that returns JSON ('数据抓取能力...返回结构化 JSON'), implying a read operation, while annotations declare destructiveHint: true. No destructive or write-side effect is disclosed, even though the example action 'post' could imply one, so an agent receives contradictory signals about the tool's safety. Pricing and no-charge-on-failure details are additive, but the contradiction with the destructive annotation dominates.

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?

Four dense sentences, each carrying distinct information: purpose, cost, limit strategy, and prerequisite lookup. The purpose is front-loaded and no sentence is wasted, though the pricing figures add moderate reading load for an agent scanning quickly.

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?

The description smartly routes the agent to everyinfra_list_capabilities to resolve dynamic platform/action values and max_limit, covering the biggest knowledge gap for a generic dispatcher. However, with no output schema it leaves the JSON return envelope unspecified, and the destructiveHint flag is never reconciled. For a generic tool with dynamic parameters this is adequate but not complete.

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% with example values for all three parameters, giving a baseline of 3. The description adds meaning beyond the schema by stating that valid platform/action values are dynamic and must be confirmed via everyinfra_list_capabilities, and by instructing the agent to set limit to max — guidance that compensates for the absence of enums and static value lists.

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: it calls any one of EveryInfra's data-scraping capabilities ('调用 EveryInfra 任意一项数据抓取能力') and returns structured JSON. This clearly positions it as a generic capability dispatcher, but it never explicitly contrasts itself with sibling everyinfra_search, so differentiation is implied rather than stated.

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 an explicit precondition — '先用 everyinfra_list_capabilities 确认 platform/action、必填参数和该能力的 max_limit' — and a concrete execution strategy: max out limit in one call since billing is not per-page. It does not state when to prefer a sibling tool like everyinfra_search over this generic caller, so exclusions are absent.

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