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

Annotations already declare read-only/idempotent/non-destructive, so the bar is met; the description goes further by disclosing that both English and Traditional Chinese text are returned as equally authentic originals under Cap. 5 s.4B, plus in-force status and version-valid-from. That legal-authenticity detail materially changes how an agent cites results and could not be inferred from annotations.

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 the resource and scope, and each clause carries information (spellings, bilingual returns, status field, sibling routing). The spelling examples duplicate the schema, which is the one redundant element, otherwise no filler.

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 carries the return-shape burden and does so (bilingual text, status, version-valid-from). Three params with one required and full schema coverage leave nothing an agent needs missing before calling it.

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 accepted section spellings ("2", "s2", "section 2", "14A") are already enumerated in the schema, so the description largely repeats structured data. It does clarify that cap and title are alternatives ('by Cap. number or title'), a small increment over schema text — baseline 3 fits.

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?

Specific verb+resource+scope: 'Full text of ONE section of a Hong Kong law', with accepted identifier forms spelled out. It explicitly says a long law is never returned whole and names hk_law_toc as the sibling for structure, so an agent can distinguish it from hk_law_search/hk_law_info without opening schemas.

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?

Gives the exact workflow: use hk_law_toc to find section numbers, then 'call this once per section' — a per-section invocability rule few descriptions state. The implicit exclusion (never request a whole law) and the named alternative cover when and when-not in one breath.

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