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

Annotations already carry the safety profile (readOnly, idempotent, openWorld, non-destructive), so the bar is lower. The description adds real value by disclosing pagination behavior and the return envelope ('Returns has_more and next_offset when the law has more sections than the page size'), which is not in the annotations. No auth or rate-limit notes, but none are plausibly needed for a public law lookup.

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?

Three short sentences, front-loaded with what the tool returns, then when to use it, then the paging contract. Every sentence earns its place with no filler or repetition of the name.

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 correctly picks up the burden of explaining the return shape (has_more, next_offset) and what the rows contain (section number and heading in order). It omits what to do when the cap-based lookup fails or what an entry object looks like exactly, but that is a minor gap for a browse tool with fully documented parameters.

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 and the schema already documents cap, limit, title, and offset. The description goes further by explaining how limit and offset interact with the has_more/next_offset response fields, which gives the paging parameters meaning the schema alone 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?

States a specific verb and resource ('Table of contents for one Hong Kong law: every section number and heading, in order, paged'), which is immediately distinguishable from hk_law_section (reads one section), hk_law_info (metadata), and hk_law_search (finds laws). An agent can pick this without opening the 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?

Names the explicit alternative and the condition selecting it: 'Use to browse a law's structure before reading a specific section with hk_law_section, or to enumerate every section number a long Ordinance has.' This gives both a primary use case and a second scoped use case with the sibling named.

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