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

Annotations already cover read-only, non-destructive, open-world, and idempotent behavior. The description adds useful operational details beyond that: it returns 'lightweight rows' containing profileUrl and mergedUrl, and it recommends a separate tool for citation-safe detail. This gives the agent expectations about result shape and the need for follow-up.

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 three brief sentences with no filler. The main purpose and search keys are front-loaded, the optional source filter is given in one clause, and the output/next-step guidance is concise. Every sentence carries operational value.

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 search tool with no output schema, the description adequately hints at return rows and the proper follow-up tool for detailed data. It does not exhaustively list all result fields or edge cases, but combined with annotations and a fully self-described parameter schema, it gives sufficient context for correct invocation.

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?

All four parameters are already described in the schema, so the baseline is 3. The description adds meaningful detail on q (name, address, licence number, registryId) and gives examples of the source enum, but it does not go deeper on limit or country semantics. This is good but not exceptional compensation over the schema.

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 states a specific action ('Search'), a clear resource ('Hong Kong official registry records'), and the searchable keys (name, address, licence number, registryId). It is distinct from the sibling tools in function, though it does not explicitly name and differentiate itself from get_registry or search_agents.

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 clear context for when to call the tool: when you need to search official Hong Kong registries by common identifiers, with optional source filtering. It also routes a follow-up use case ('follow up with get_merged_profile for citation-safe detail'). However, it does not explicitly state when to prefer get_registry or search_agents instead.

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