【生成 Table 1（基线特征表）】 用户有数据文件，要出论文第一张基线表 Table 1 返回：Table 1 表格 + 可选段落 （真实算法引擎执行，非大模型生成）
| Name | Required | Description | Default |
|---|---|---|---|
| file_id | No | 数据文件 id（可不填，助手会自动用你最近上传的数据） | |
| test_method | No | auto/t/nonparametric/chi2 | |
| group_variable | Yes | 分组变量列名 | |
| generate_paragraph | No | 是否同时生成论文表述段落 | |
| variables_to_include | No | 纳入的变量列名 |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already establish that this is a non-destructive, non-open-world read operation. The description adds two useful behavioral facts beyond them: the return payload (table plus optional paragraph) and the guarantee that a real algorithm engine, not an LLM, performs the computation. It says nothing about how the grouping or test-method choices affect output, so the added disclosure is modest.
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?
It is short, front-loads the bracketed purpose, and wastes no words. The telegraphic style and mixed bracket label, trigger, return, and engine note in one run-on line keep it slightly below fully polished structure.
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?
With 5 parameters mostly covered by the schema and no output schema, the description fills the main remaining hole by describing what comes back (table plus optional paragraph). What is missing is the prerequisite that a data file must exist and how that interacts with the optional file_id.
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% and every parameter, including the optional file_id fallback and the test_method options, is documented in the schema. The description adds no additional meaning about field semantics, so the baseline of 3 applies.
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 states a specific verb and resource combination (generate Table 1, the baseline characteristics table) and notes the paper-facing context. It does not distinguish the tool from the sibling act_table_one_subgroup, so an agent facing both must infer the difference from the names alone.
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 implies the trigger condition (the user has a data file and wants the first baseline table of a paper), which is enough to suggest when to call it. It gives no when-not guidance, no prerequisites such as data being uploaded first, and never names the subgroup variant as the alternative.
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.