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

Annotations already establish readOnly/idempotent/non-destructive, and the description goes beyond them with genuinely useful behavior: out-of-range dates fail with an error listing valid dates, ETFs are excluded, and attribution must be preserved for licensing with computed_by_livermore flagged as non-official. It does not cover auth or rate limits, so it is strong rather than exhaustive.

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 purpose and routing are front-loaded in the first two sentences, and the trailing 'Taiwan conventions' block is dense but earns its space by defining currency, lot size, and _pct fields. The single run-on paragraph is heavy and would scan better broken into short sections, which is the only reason it is not a 5.

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?

An output schema and annotations exist, and the description still supplies everything needed to call and interpret the tool: date window, enum meanings, per-row field definitions, units/currency conventions, language/URL caveats, and attribution obligations. Nothing material for correct invocation or interpretation is missing.

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; the description earns extra by restating category/side/days semantics in context and, more importantly, explaining what the parameterized period produces (net_shares as period total, estimated_value as summed daily net shares times close, period_change_pct measured against the base_date close). That adds meaning the schema does not.

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 opening sentence names a specific verb (bought/sold) and resource (Taiwan companies) and pins the exact scope: one investor category, 1/5/20 trading days ending on a date, companies only (no ETFs). It even distinguishes itself from the sibling tw_get_daily_trading by name, so an agent can route 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 states the operating window explicitly ('date must be one of the latest 30 trading days with institutional data (recent_dates); other dates return an error listing them') and names the alternative tool for a different task ('Use tw_get_daily_trading for one stock's daily history'). When-to-use, constraint, and alternative are all present.

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