phrase_trend

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

With no annotations provided, the description carries the full burden and delivers richly: it discloses time-bucket zero-filling (disappearance itself a signal), the per100 saturation at 100 for high-frequency words, and the noise caveat for small buckets (n<20). These are exactly the behavioral traits an agent needs to interpret results correctly and are beyond anything in the schema.

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 core purpose and metrics are front-loaded, with caveats stacked afterward. Every sentence earns its place — saturation, noise, and zero-fill are all load-bearing. It is dense and slightly long, with several warnings packed together, but efficiency is strong overall.

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?

Given no output schema and no annotations, the description covers the essential semantics well: metrics, saturation, noise, zero-fill, and a usage example. The main gap is that the return/output format is never described, and the granularity parameter's accepted values are unstated. Still, an agent can likely call this correctly for its core use.

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 0%, so the description must compensate. It illustrates the 'phrases' parameter with concrete contrast examples (高质量发展 vs 高速增长) and clarifies time-bucket semantics, partially compensating. However, the 'granularity' parameter (default year) is never mentioned in the description, so one of two params remains undocumented beyond the schema.

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 states a specific verb+resource: it computes per-phrase trend metrics (coverage articles/per100 and intensity per10k_chars) across time buckets. This is clearly distinct from siblings like search or get_article, which retrieve content rather than aggregate temporal signal. The CMP methodology framing further sharpens what the tool produces.

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 gives a concrete recommended use case — '适合对比同义/竞争提法' (suitable for comparing synonymous/competing phrases) with an explicit example. However, it never names alternative tools or states exclusions, so an agent must infer when this beats a sibling like topic_timeline. Guidance exists but 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.