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

Annotations already establish readOnly/openWorld/idempotent non-destructive behavior, and the description adds substantial context: data source, weekly update cadence, substring/case-insensitive name matching, exact BR number matching, and the confidence-gated HKEX ticker join ('only attached on a confident name match, never guessed'). The limitation about the 2024-12-30 cutoff and unavailable fields is clearly disclosed and does not contradict 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?

The description is dense but well-organized: purpose, matching behavior, return fields, limitation, and example use cases. Every clause contributes critical information, especially the limitation context. It is longer than average, which is justified for a tool with non-obvious scope constraints, though it could be slightly tightened.

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 enumerates all return fields (BR number, English/Chinese names, company type, dates, optional HKEX ticker) and explains the data window, default since behavior, and the unavailable fields. It gives an agent everything needed to decide whether this tool fits the query and to set parameters correctly.

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 the baseline is 3. The description adds value by clarifying that name and brn are alternative match keys ('Match by company name ... or an exact BR number'), and by explaining the semantic effect of name matching on returned tickers. This goes modestly beyond the schema's per-parameter descriptions.

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?

The description opens with a specific verb, resource, and scope: 'Search Hong Kong companies newly incorporated, registered, or renamed ... since 30 Dec 2024'. It also disambiguates from siblings by explicitly stating it is NOT the full historical company register and by covering new/renamed entities, which separates it from hk_new_companies, hk_company_name_changes, and hk_company.

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?

The description gives explicit use cases ('Use for "is there a new HK company called X", "HK BR number for Y", ...') and clear exclusions ('NOT the full historical company register', no address/status outside the window). However, it does not name sibling tools like hk_company, hk_new_companies, or hk_company_name_changes as alternatives, so an agent must infer which sibling to route to.

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