NewTimeSpace News

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld, so the safety profile is covered. The description adds value beyond them: the batch cap of 10 IDs, that the body is returned as Markdown, and that scripts/styles have already been cleaned as noise. It does not discuss truncation or error behavior for invalid IDs, which keeps it from a 5.

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?

Three short lines with zero waste: purpose first, then when-to-use, then the batch limit and return format. Front-loaded and scannable, with no filler.

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 an output schema present the description need not explain return values, and it still characterizes the body format (Markdown) and cleanliness. Combined with full schema coverage and clear annotations, an agent has everything needed to call this correctly after a search.

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 both parameters are already documented including the enum for language. The description still reinforces the comma-separated ID format and the 10-ID ceiling, which matters operationally even though it restates the schema. No added meaning for the language parameter beyond what the enum provides.

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 uses a specific verb+resource (获取文章详情 / 单篇或多篇资讯的完整正文与详细元数据) and states the scope: single or multiple articles by ID, Markdown body plus metadata. It distinguishes itself from the only sibling, search_articles, by framing itself as the follow-up step for full 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?

The 调用时机 line explicitly names the alternative (search_articles) and the condition that selects this tool: after finding target news, when deep analysis, summarization, translation or detail extraction is needed. That is an explicit when-to-use plus a named prerequisite, which is the top of the scale.

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

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

Annotations already establish read-only, idempotent, non-destructive open-world reads, and the description adds real behavioral context on top: default responses return only summaries plus metadata to conserve tokens, and an invalid category does not error but returns an authoritative category list in warnings. It does not cover pagination totals or rate limits, so it stops short of a 5.

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 token-saving default and the full-text workflow are front-loaded before the bracketed per-parameter sections, which an agent can jump to selectively. It is longer than needed because the query/category/date sections restate what the schema already documents.

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?

For a 10-parameter, zero-required search tool with an output schema present, the description covers the retrieval workflow, token tradeoffs, the category discovery fallback, and how to escalate to get_article_detail. No caller decision is left unanswered by the combined description, schema, and annotations.

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 baseline is 3, but the description adds meaning beyond it: category must be paired with language and matched case-sensitively, the placeholder-category retry loop, and the open-interval semantics of supplying only one date bound. Some of this duplicates the schema text, which caps the score below 5.

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 opens with a specific verb and resource (search and retrieve NewTimeSpace news articles) and lists the covered domains (finance, tech, IPOs, ETFs, overseas). It explicitly distinguishes itself from the sibling by naming get_article_detail as the tool for full article body, so an agent can route correctly without opening either schema.

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 explicit when-to-use rules per parameter: single core entity term only for query, empty query with page=1 for "latest news" requests, same-day filtering via identical start/end dates, and the include_content vs get_article_detail decision path. It also states when-not to pass compound or boolean queries. This is unusually complete routing guidance.

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