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

The annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the description does not need to restate safety. It adds the genuinely useful claim that results come from a real algorithm engine rather than LLM generation, which tells the agent how much to trust the output. It does not disclose what clustering or preprocessing must precede the call, or what happens when groups are absent.

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 description is two short clauses with a bracketed label up front and the return value and trust note afterwards. Nothing is wasted, though the terse phrasing leaves the scope boundary between sibling tools unstated.

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 stating 返回：各群 marker is helpful. However, the description omits prerequisites, such as whether clustering must already exist or whether groups is required for this tool. For a single-parameter tool with a richly documented schema, it is adequate but incomplete.

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 the data_json field already documents the matrix, rows, cols, and optional groups, p_values, and log2fc structure in detail. The description adds no parameter meaning beyond that, 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 names a specific verb and resource: find marker genes for each cell cluster (各细胞群的 marker 基因). That distinguishes it from generic scRNA siblings such as act_scrna_analyze and act_scrna_celltype. However, those siblings are not named, so the boundary is inferred rather than stated.

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 phrase 用户要找各细胞群的 marker 基因 implies when to call (when the user wants per-cluster markers). The description does not say what the tool requires as input, such as clusters or groups, or when to use act_scrna_celltype or act_scrna_analyze instead. The guidance is therefore implicit only.

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