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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral claim — that results come from a real algorithm engine, not LLM generation — which tells the agent the output is deterministic and trustworthy. It omits runtime/cost expectations for what is a potentially heavy computation and says nothing about input format expectations.

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?

Two compact clauses: purpose first, then return values, with the engine-authenticity note appended. Nothing is padded, though the leading bracketed '【单细胞分析】' largely restates the annotation title and could be dropped.

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 no output schema, the description correctly states what comes back (clustering results and UMAP), which is the main completeness requirement. However, data_json is a nested object whose expected structure (genes × cells orientation, accepted value types) is unexplained anywhere, and the QC parameters' effects on filtering are not described — a real gap for a tool with nested input.

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 four parameters (n_pcs, data_json, min_genes, max_mito_pct) are already documented in the schema, establishing the baseline of 3. The description adds no interpretation of these knobs, such as defaults or how n_pcs interacts with clustering quality.

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 analysis verb pair (聚类降维 = clustering + dimensionality reduction) on a specific resource (single-cell data), which separates it from marker/cell-type siblings like act_scrna_markers and act_scrna_celltype. It does not explicitly name those siblings, so the differentiation is inferential 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 '用户有单细胞数据要做聚类降维' implies the triggering condition (user has scRNA data and needs clustering/UMAP), which is adequate usage context. It gives no explicit when-not guidance, no mention of prerequisites (e.g., normalized matrix required), and no routing to alternative scRNA tools.

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