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

Annotations already mark read-only/idempotent, and the description adds meaningful behavioral context beyond that: rolling 30-day window, data source (GDELT Global Knowledge Graph), return fields (headline, publisher, URL, publication time, themes, tone), and the limitation 'Article metadata only... no article text.' No contradiction.

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?

Five sentences, each earning its place: purpose + outlets, filters + returns, use case, metadata-only caveat, rolling window, and pointer to sibling. Dense but not padded; information is front-loaded.

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 7 optional params fully covered by schema, no output schema, and readOnly annotations, the description covers everything needed for correct invocation: what it returns, the 30-day coverage, absence of article text, and how to discover searchable publishers.

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?

Input schema has 100% coverage across all 7 parameters with detailed descriptions (e.g., lang explains host-based English editions, region enumerates cn/hk/tw/overseas). The description only restates high-level filter dimensions (keyword, publisher, jurisdiction, language, date), adding no semantics beyond the schema, so 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?

Description opens with 'Search recent news coverage from Chinese, Hong Kong, Taiwanese and overseas-Chinese publishers' — a specific verb, resource and scope. It enumerates recognizable outlets, lists the filter dimensions, and implicitly separates itself from china_news_article by stating it returns metadata, not article text.

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?

Explicitly states when to use it: 'Use it to see how mainland state media, Hong Kong and Taiwanese outlets are covering a topic, and how that differs.' It also says 'Call china_news_outlets to see exactly which publishers are searchable,' naming the alternative, and defines a boundary with 'there is no article text — follow the url.'

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