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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds useful scope detail — that values are daily/per-session and include turnover, volume and transaction count — but says nothing about return format, latency or history limits beyond what the schema-adjacent text implies.

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?

Two tightly written sentences: the first defines scope and metrics, the second enumerates the intents it serves. Nothing is redundant and the most informative content 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?

With no output schema, the description usefully enumerates the returned metrics, and a single optional parameter plus read-only annotations means little else is needed. Minor gap: no indication of data freshness or how many sessions are returned by default, though the schema covers the latter.

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% and the single 'days' parameter (1-30, default 5) is fully documented in the schema, so the baseline is 3. The description never references the lookback parameter, meaning it adds no semantic value over the schema.

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?

States a specific resource (TAIEX and TPEx OTC index) with the exact metrics returned (level, change, turnover, share volume, transaction count) per session. It is unmistakably a market-wide summary, differentiating it from single-instrument siblings like taiwan_stock_quote or taiwan_top_traded.

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 quoted example questions ('where did the TAIEX close', 'how is the Taiwan stock market doing', 'Taiwan market turnover this week') give the agent concrete intent-matching cues for when to select this tool. However, it names no alternatives or exclusions, so routing against neighbouring Taiwan tools is left to inference.

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