deepseek_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: real-time results, relevance scores exposed as rerank_score, and dense LLM-tailored summaries. It also flags advanced query syntax support ('site:', '-site:', quotes). It does not mention auth requirements, rate limits, cost, or error behavior, keeping it 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 short sentences, front-loaded with purpose, then output characteristics, then syntax support. No filler; each sentence conveys distinct information (what it does, what it returns, how to query it).

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?

No output schema exists, and the description usefully covers return values (rerank_score, summaries), so the agent knows what to expect. With 100% schema coverage on parameters, the remaining gap is guidance on tool selection versus deepseek_fetch and operational constraints (limits, auth), which would push it to a 5.

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 the schema already documents count, min_score, detail_level, localization, and ori_question thoroughly. The description only reinforces the query-syntax aspect already covered in the schema's query field, adding no meaning beyond it. Baseline 3 applies when the schema does the heavy lifting.

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 a specific verb and resource: 'Search the web using DeepSeek's official search engine.' The verb 'search' inherently contrasts with the sibling deepseek_fetch ('fetch'), so an agent can route between them without opening either schema. It also names the engine provider, removing ambiguity about which backend is used.

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?

Usage is implied ('search the web' for real-time results) but the description never states when to prefer this over deepseek_fetch, nor any prerequisite such as needing a URL first. No when-not guidance or explicit alternative is given, leaving the agent to infer the search-then-fetch workflow.

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