使用 DeepSeek API 生成文本 (需要 DEEPSEEK_API_KEY)。
Args:
prompt: 用户提示词
model: deepseek-flash 或 deepseek-v4-pro
temperature: 生成多样性
max_tokens: 最大输出 token 数
top_p: Top-P 采样参数
system_instruction: 系统指令
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | deepseek-flash | |
| top_p | No | ||
| prompt | Yes | ||
| max_tokens | No | ||
| temperature | No | ||
| system_instruction | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose a genuine behavioral prerequisite (DEEPSEEK_API_KEY) and implies a text return, but says nothing about cost, rate limits, latency, error behavior, or failure modes for what is an external API call.
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?
The purpose is correctly front-loaded in the first line, but the Args block is largely a restatement of parameter names with minimal added meaning, spending space without earning much.
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 6-parameter external-generation tool with no output schema and no annotations, the description covers the inputs at a basic level and flags the API-key requirement. It omits the return shape/format and any operational constraints, leaving an agent without enough to predict call behavior.
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 0%, so the description must compensate and it lists all six parameters. The explanations are thin (mostly restating names, e.g. 'temperature: 生成多样性'), but the model line adds real information not in the schema by naming the valid options 'deepseek-flash 或 deepseek-v4-pro' (no enum exists in the 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 states a specific verb+resource ('使用 DeepSeek API 生成文本'), which is clear and, via the provider name, implicitly distinguishes it from siblings like generate_with_vertex and call_dashscope_mcp. It does not explicitly state when to prefer this provider over those siblings, keeping it short of a 5.
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?
The only contextual guidance is the parenthetical requirement of DEEPSEEK_API_KEY. There is no when-to-use, when-not-to-use, or comparison against the many sibling generation/optimization tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.