search_web

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

With no annotations, the description carries the full behavioral burden. It does disclose the latency tradeoff (default fetch_top 0 keeps latency low), that content fetching is concurrent plain HTTP with ~800 characters per snippet, and the numeric bounds (1-20 results, 0-3 fetches). It says nothing about rate limits, failure modes, or throttling, which matters for a scraping-backed search tool.

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-loaded one-line purpose followed by a compact parameter block; each parameter note earns its place with a default or a use case. Slightly verbose but no filler sentences.

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?

An output schema exists, so return values needn't be spelled out, and all five parameters are fully documented. The only gap is failure/rate-limit behavior, which is forgivable given the output schema and complete parameter coverage.

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 compensate and it does: every one of the five parameters gets meaning, valid values, and defaults — region enumerations (wt-wt/cn-zh/us-en), timelimit codes (d/w/m/y), result caps, and the 0-3 fetch_top range. It explains far more than the bare schema.

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 first line names a specific verb (联网搜索 / web search), the engine (DuckDuckGo), and the return shape (a result list with links). It implicitly separates itself from search_github and fetch_url_content by being a general web search, but never names those siblings explicitly.

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 real selection guidance: use timelimit "w"/"d" for news queries, and set fetch_top to 2-3 when you want direct answers instead of fetching results one by one — which routes the agent away from the sibling fetch_url_content. It lacks explicit when-not-to-use or a direct comparison to search_github.

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