stock_market_summary

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

With no annotations, the description has to carry the load, and it does disclose the most important trait: the data is end-of-day, not real-time, with separate dates per market. It says nothing about data source authority, refresh/caching behavior, error conditions, or the exact response shape beyond the listed fields.

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 facts — what data, what freshness, no params — are front-loaded in the first sentence. The English sentence largely mirrors the Chinese one, which is defensible for a bilingual audience but is not strictly additive.

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 parameterless read-only summary with no output schema, the description successfully substitutes for a schema by enumerating the returned metrics and warning about staleness. Only the absence of any response structure or units detail (beyond 張 for margin balances) keeps it from full completeness.

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?

The tool takes zero parameters, so the baseline is 4, and the description reinforces this by stating no parameters are required, which prevents an agent from inventing a date or market argument.

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 concrete resources: TWSE weighted index, TPEx index closing change, trading value, and margin/short balances (in lots). This is clearly a market-wide closing summary rather than an individual stock lookup, which implicitly separates it from sibling stock_quote, but no sibling is named explicitly.

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 note '盤後資料，非即時' (post-close, not real-time) and '無需參數' give useful calling context, and the market-wide scope implies when to prefer it over a single-quote tool. However, there is no explicit statement of when not to use it or which sibling to pick for a specific stock or dividend question.

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