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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and with no output schema the description carries the return-value burden — it does so richly, disclosing level, category, official English title, abolished status, article count, and the subtle last_amendment vs effective date split with the effective_date_pending flag. The Taiwan-specific amendment/effect nuance is exactly the kind of context annotations can't express.

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 lookup keys are front-loaded, and the long second clause is dense with genuinely useful return-field detail rather than padding. It is a single-sentence wall, though, which makes the amendment/effect distinction harder to skim than a short list would.

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?

For a two-optional-param, read-only lookup with no output schema, the description supplies purpose, routing, and a near-complete account of the returned metadata. The remaining gap is behavioral: with zero required parameters, the description never says what the tool does or errors on when neither pcode nor name is provided.

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%, so both parameters are already documented (including 'exact or partial'), and per the baseline this yields a 3. The description adds only the framing that name is used 'when pcode is not known'; it does not clarify precedence when both are passed or what happens when neither (0 required params) is supplied.

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+resource ('Resolve a Taiwan law to its full metadata') and names the two lookup keys. It explicitly positions itself against siblings ('from tw_law_search' for the pcode, 'the exact-citation step before reading an article' for tw_law_article), so an agent can place it in the workflow without opening any 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?

Explicitly says the pcode comes from tw_law_search and that this is the step preceding article reading, which effectively routes the agent between the three tw_law_* tools. It stops short of naming exclusion cases or stating what to do when neither identifier is supplied.

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