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

Beyond the readOnly/idempotent annotations, it discloses several traits the agent cannot get from structured fields: per-call billing cost, the point-in-time panel policy (no lookahead), the 15:00 intraday cutoff when as_of_date is supplied, and that up to 20 participating agency_ids are returned. These are exactly the operational details that matter for a data-query tool.

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 purpose and weighting rule are front-loaded in the first two clauses, followed by methodological caveats and cost. The formula sentence is dense but load-bearing; a small amount of redundancy exists between the title and the opening sentence.

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 must explain returns, yet it only mentions participating agency_ids (max 20) and never lists the per-stock fields the caller should expect (code/name, weighted_heat, mention count). For a tool with six parameters and a custom aggregation, that leaves a real gap in what the response will look like.

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 the schema does not: min_score's default 1050 corresponds to roughly the top 10% of sources, and as_of_date changes the underlying message window rather than just a label. The weighted_heat formula also explains how the default 'weighted' ordering value is produced.

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 a specific resource and method: a hot-stock ranking weighted by the score of high-credibility institutions/KOLs, with an explicit weighted_heat formula and a default source-score threshold of 1050 (~top 10%). This implicitly separates it from unweighted siblings such as get_market_hot_stocks, though no sibling is named outright. The only blur is the closing line about returning agency_id, which sits oddly next to a stock-ranking title.

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 states the selection criterion (only mentions from sources scoring above the threshold) and a concrete use case: passing as_of_date truncates messages to 15:00 that day, which makes it suitable for backtesting. There is no explicit when-not or named alternative (e.g., versus get_accelerating_hot_stocks or get_first_mention_stocks), so the agent must infer exclusion conditions.

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