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

Annotations already declare readOnly/non-destructive/closed-world, so the safety profile is covered. The description adds only the return contents ('聚类结果与 UMAP') and omits a meaningful behavior: min_genes and max_mito_pct mean this tool also performs QC filtering before clustering, which is a non-obvious side effect of a tool titled 'cluster'.

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?

Pipe-delimited fields front-load the purpose, trigger, aliases, and return value with no filler. It is slightly telegraphic, but every segment carries 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?

For a 4-parameter tool taking a nested object matrix and returning no output schema, the definition covers purpose and rough returns, which is adequate. The gap is the data_json matrix format — its internal shape is unstated in both schema and description, leaving the required parameter underspecified.

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 schema already documents all four parameters and the baseline is 3. The description adds no interpretation of n_pcs, min_genes, or max_mito_pct beyond their schema text, and gives no hint about the expected structure of the nested data_json matrix.

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?

States a concrete operation ('cluster and embed single-cell data (UMAP)') on a concrete resource, which is clearly distinct from scrna_annotate, scrna_markers, and flow_cluster. It stops short of naming those siblings, so an agent must infer the boundary rather than being told it.

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 'USE WHEN' clause gives an explicit trigger condition, which is more than most definitions offer. It does not say when to avoid this tool or route to scrna_annotate/scrna_markers instead, so the alternative-selection guidance is incomplete.

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