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

Annotations declare openWorldHint=false, but the description routes to web search, news, crawl, forum, and scholar, all of which retrieve from external internet sources. That directly contradicts the closed-world annotation. The description does add useful billing/fallback context, but the contradiction forces a 1 under the rubric.

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?

Front-loads the dispatch rule and uses a compact list for the 17 sub-tools. The description is long, but the length is largely justified by the number of routing options; a few explanations are more verbose than necessary but still help selection.

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?

For a 17-way dispatcher with no output schema, the description supplies behavioral and output hints: map returns URLs only, crosscheck returns layered sources, read has fallback, harvest is long-running, and failed/empty results have billing recovery. It omits auth/rate-limit details and full return semantics for every sub-tool, but is largely 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% for the top-level `tool` enum and `params` object, but nested per-tool parameters are not documented in the schema. The description compensates by adding meaning for several sub-tools: deep `full=true`, scholar `kind=patents`, semantic `mode=deep`, and web support for site/region/time/pagination.

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?

States '检索' and that 17 sub-tools are selected via the `tool` parameter, then enumerates each sub-tool. The dispatch purpose is clear, though it does not explicitly distinguish the parent everyinfra_search from sibling tools such as everyinfra_call_api.

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?

Gives explicit routing rules: use crosscheck when asserting specific facts, use harvest only when crawl cannot get content, use lens for reverse image search versus media, and treat forum as an independent evidence source. It provides when-to-use and when-not-to-use guidance among the 17 sub-tools.

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