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

Annotations already establish readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description still adds real behavioral context beyond them: route-dependent defaults (query→time, trending→hot, scoped browse→time-only), Telegram's internal ten-category fan-out with cross-category dedup and one global newest-first stream, and Twitter's two independent recall legs with split quota and backfill. It does not cover pagination, rate limits, or failure modes, so it falls 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?

Purpose/COVERS/BOUNDARIES/USAGE/RETURNS/EXAMPLES headers make it navigable and the routing rules are front-loaded, which is a strength for a complex tool. However, the USAGE section duplicates parameter documentation that already lives in the schema (sort_by per route, Telegram fan-out, source_lang), and the 12 cross-lingual examples add bulk; the text is denser than it needs to be.

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 does carry the return burden and discharges it: article/document rows with title, content, source, author, time, and a source-quality tag, plus a pointer that ticker-scoped report cards live under metrics.fundamentals. Combined with the routing guidance and examples, an agent has enough to invoke it correctly; only pagination/error behavior is unaddressed, which keeps it off a 5.

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 description coverage is 100%, so the baseline is 3, and the description largely restates schema content — the sort_by route rules, limit budget semantics, source_lang language list, and the empty-query/trending behavior all already appear in the schema. The one genuinely additive element is the cross-parameter pattern for KOL lookup (handle in query + sources=["twitter"], e.g. 马斯克→elonmusk), which does not fully lift it above the baseline.

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?

Opens with a specific verb+resource ('Search financial news, market commentary, social posts, and raw indexed research-source articles/documents') and immediately scopes the covered content types (articles, tweets, Telegram posts, blogs, media, research documents). It also explicitly separates itself from siblings (metrics, signal, twitter) rather than leaving the agent to guess.

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 BOUNDARIES block gives explicit when-not routing: commentary/interpretation → news, raw numbers and structured 研报/cards/ratings → metrics, KOL consensus/喊单 → signal, a named account's complete timeline or a tweet's replies → twitter. It also states the trigger for the trending route (empty query, no sources) and when source_lang applies.

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