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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description does add one genuinely useful behavioral fact — that a real algorithm engine executes the scoring rather than an LLM — which builds trust in the numbers. It says nothing about validation behavior (e.g. whether percentages must sum to 100 or how missing intensities are treated).

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?

Extremely compact and front-loaded: the label, trigger condition, and return values all appear in a single sentence with no filler. The only inefficiency is that the return list duplicates information already implied by the leading label.

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 usefully states what is returned (H-score / Allred / 阳性率), which is the right thing to include. For a 5-parameter calculation tool it still omits the accepted stain_type values and any constraint on the four percentage inputs, leaving real ambiguity about how to call it correctly.

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 baseline is 3. The description adds no parameter meaning beyond the schema and never mentions stain_type, which is the one required parameter and has no enum — the valid stain type values (and whether they select which score is computed) are left entirely undocumented in both schema and description.

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+resource (IHC 免疫组化评分) and enumerates the concrete outputs (H-score / Allred / 阳性率), so an agent knows exactly what computation this performs. It does not differentiate from nearby pathology-scoring siblings such as act_gleason or act_fibrosis_stage, but the domain is unambiguous.

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?

"用户有 IHC 染色结果要算..." gives a usable trigger condition (user has IHC staining results and wants these scores). However, there are no exclusions, no prerequisites, and no pointer to any alternative tool, so the guidance is implied rather than explicit.

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