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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds nothing beyond that: no mention of which statistical method is used, minimum cluster size, whether groups are auto-derived from cols, or any runtime expectation. 'RETURNS: 各群 marker' is a restatement, not behavioral detail.

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 definition is short and front-loads the purpose and trigger, which is good. The ALIASES block is largely padding for an agent consumer, and the RETURNS line occupies space without conveying information.

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 and a nested-object input, the description should explain what comes back — a table of markers per cluster with p-values/log2FC columns, for example — but only says '各群 marker'. For a per-cluster marker computation whose result shape drives downstream use, this leaves a real gap.

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?

There is a single required parameter and schema description coverage is 100%, with the schema itself fully spelling out the matrix/rows/cols/groups/p_values structure. The description adds no additional meaning about data_json, so the baseline 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 the resource (single-cell marker genes) and, via 'USE WHEN: find marker genes per cluster', a specific operation and scope, so an agent can tell it computes per-cluster markers. It does not distinguish itself from nearby siblings such as scrna_cluster, scrna_annotate, or differential_expression, which keeps it below 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?

'USE WHEN: find marker genes per cluster' supplies an explicit trigger condition, which is more than nothing. However, there are no exclusions and no named alternatives, so an agent choosing between this and differential_expression or scrna_annotate gets no routing help.

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