deepseek_web_search

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: it states the structured return shape and, unusually, the billing model (5 yuan per 1000 successful requests, failures not billed). It omits rate limits, auth requirements, and result pagination behavior, so it stops short of a 5.

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?

Three compact sentences with the core purpose front-loaded, followed by syntax then pricing. Nothing is redundant or padded, though the operator list is dense and could be slightly better formatted.

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 must cover returns, and it lists the result fields explicitly. Combined with query syntax and pricing, it is largely complete for a 5-parameter search tool, with the only real gap being when to prefer it over deepseek_fetch.

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 100%, so a baseline of 3 applies, but the description adds real value beyond the schema by documenting the query mini-language (site:, -keyword, "exact phrase", lang:, after:/before:) that the schema does not express. It adds no interpretation of count, localization, need_content, or ori_question.

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 specific verb and resource ('search the web' with DeepSeek's own engine) and enumerates the returned fields (title, URL, date, relevance, snippet), so the intent is unmistakable. It does not explicitly contrast itself with the sibling deepseek_fetch, so the sibling-differentiation criterion for a 5 is not fully met.

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?

There is no guidance on when to choose this tool over deepseek_fetch or any other alternative, and no stated prerequisites or exclusions. The query-operator syntax is useful but is parameter detail rather than selection guidance.

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