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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: null semantics for missing data, the caveat that AI-written sections 'may contain errors' with annual_report_url as the authority, and a mandatory attribution/licensing requirement naming Taiwan's Open Government Data License. These are behavioral facts the agent cannot get from annotations or schema.

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?

Front-loaded with purpose and organized by output section, which aids scanning. However, the long field-by-field enumeration of the response duplicates what the output schema already provides, so a meaningful fraction of the ~350 words does not earn its place; it is thorough but over-long for a one-parameter tool.

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?

Given an output schema exists, the description need not restate return values, yet it still supplies the interpretive layer an agent needs: currency and unit conventions, percentage semantics, market codes (TWSE listed vs TPEx OTC), Traditional Chinese naming, and the attribution obligation. Nothing material 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% and the single `code` parameter is fully documented in the schema, including formats and the tw_search fallback. The description adds only the general Taiwan conventions block (TWD, lots of 1,000 shares, _pct fields), which is mostly about output interpretation rather than the parameter itself, so the baseline 3 is appropriate.

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 verb and resource ('Overview of one Taiwan stock or ETF (TWSE or TPEx) by code') and immediately enumerates the data sections it returns, so the agent knows exactly what it gets. It also distinguishes itself from siblings by naming tw_get_daily_trading, tw_get_financials, tw_get_monthly_revenue and tw_get_industry_chain as the tools for adjacent data.

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?

Explicitly routes the agent: 'For price history and daily institutional, margin, securities lending and foreign holding data use tw_get_daily_trading', and defers full statements to tw_get_financials and whole chains to tw_get_industry_chain. It also notes the ETF edge case ('ETFs and other securities usually have only security, quote and dividends'), which is real when-to-use guidance.

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