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

Annotations already cover safety (readOnly/idempotent/non-destructive), yet the description goes well beyond them: it discloses the data source and licensing obligations, distinguishes government open data from Livermore-computed fields (computed_by_livermore), specifies ordering rules (listed by market cap, then ESB/GISA which lack quotes), currency/unit conventions, and error behavior for unknown codes.

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?

Purpose and the three modes are front-loaded and every clause carries information, but the single dense paragraph mixes tool-specific behavior with a generic 'Taiwan conventions' block that reads as boilerplate appended across the tw_ family, making it heavier than strictly necessary.

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 an output schema present the description need not document return values, and it still covers scope, all three modes, ordering, localization (Traditional Chinese names/streams), attribution requirements, and error semantics. Nothing an agent needs to call it correctly 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, but the description adds genuine meaning beyond the schema: it explains how `chain` and `segment` interact to change the result shape, that `limit` applies per segment with listed companies ordered first, and that sub-segments carry parent_code.

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 (get) and resource (Taiwan's industry value chains from the TPEx platform), gives a concrete scope example (47 chains, semiconductors, D000) and the core use case ('to find companies by what they do'). It is clearly distinguishable from sibling tw_get_stock, which it explicitly names as the per-company counterpart.

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?

Enumerates all three invocation modes and their distinct outputs: no chain (all chains with code, name, company counts), chain (segments in platform order with companies), and chain+segment (segment plus sub-segments only). It also routes to the alternative (tw_get_stock shows the segments of one company) and notes that unknown codes return an error.

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