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

Annotations already declare openWorldHint=false, destructiveHint=false, and readOnlyHint=false, so the description's job is to add context beyond that — and it adds almost none. 'RETURNS: 国自然分析' merely restates the tool name, with no indication of what the analysis contains, whether the 'odds' are model-generated or heuristic, or what the caller should expect. The notable oddity of readOnlyHint=false on a pure analysis tool is never addressed.

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 pipe-delimited, label-prefixed layout is front-loaded and scannable, and the alias list genuinely aids matching on Chinese terms. However, 'RETURNS: 国自然分析' is a pure tautology that occupies a slot without conveying information, and the bilingual duplication of the title adds bulk without new meaning.

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 is the only place the return value could be described, and it fails to do so — an agent cannot tell whether it gets a category recommendation, a probability, a rationale, or prose. For a single-input tool this is the one gap that matters, and it is left open.

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, 'disease', and the schema documents it at 100% coverage ('疾病/研究方向'). The description never mentions the parameter or clarifies how broad or narrow the input should be, so it adds nothing beyond the schema — 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 a specific resource and verb combination ('NSFC grant fit analysis') and enumerates the questions it answers (topic fit, funding category, odds). That is enough to separate it from siblings such as distribution_fit, ic50_fit, or acceptance_probability, though 'analysis' alone is generic and the scope only becomes concrete in the USE WHEN clause.

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: the user asks whether a topic fits NSFC or provincial funding, which category to pick, or the hit rate. It states no exclusions and names no alternative tool for overlapping cases (e.g., when the question is about journal acceptance rather than grants), so it stops short of a 5.

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