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

Beyond the readOnly/idempotent annotations, the description discloses concrete limits (区间最长 92 天, 单次最多 20 个标的), a material caveat that weighted_heat 用当前机构分口径加权（非当日 PIT）, and a cost note (每次调用计费 1 次). These are exactly the operational facts an agent needs before calling.

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 metric list and the hard limits come first, then the caveat, then cost — a sensible order. The opening phrase duplicates the title verbatim, which is a small waste, but the rest is dense and earns its space.

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 six optional parameters, the description supplies the limits, the non-PIT caveat, and the billing note that an agent would otherwise lack. It stops short of explaining what is_first_mention_day means or what the panel rows look like, a minor gap for an export-oriented tool.

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 coverage is 100%, so the schema already documents all six parameters including defaults and the type enum, giving a baseline of 3. The description reinforces the 20-code cap and the 92-day window but adds no syntax or format detail the schema lacks.

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 and the returned metrics concretely (mentions、agencies、weighted_heat、is_first_mention_day), plus the granularity (按自然日聚合). It covers both stock and concept modes via the type parameter, though it does not explicitly contrast itself with nearby siblings such as get_stock_heat_windows.

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?

It says 适合回测与面板导出, which gives a use-case hint, but it never states when to prefer a sibling tool (get_stock_heat_windows, get_stock_news_heat) or when this tool is the wrong choice. Usage is therefore implied rather than directed.

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