Hong Kong CourtDB

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

Annotations already indicate read-only behavior. Description adds return shape ({ data } with parties, files) and null-if-not-found behavior, which is valuable context beyond 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?

Two concise sentences front-load the purpose and provide essential details without any wasted words.

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 simple 1-parameter read tool with no output schema, the description covers id format, return structure, and null behavior, making it complete for an agent to invoke 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 provides no description for 'id', but the tool description fully compensates by specifying the format (caseNo/year) and an example, making the parameter semantics complete.

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?

Description clearly states 'A single Hong Kong court case by id' with a specific verb and resource, distinguishing it from siblings like Hk_list_cases and Hk_get_document. The format and example further clarify scope.

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 implies usage when a specific case id is known, providing format and example. It does not explicitly contrast with siblings, but context makes the use case clear.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds the return shape { id, text } and the important behavior that text is null when no converted HTML exists, providing useful context beyond annotations. No contradiction.

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?

Two sentences, front-loaded with the main purpose and immediately specifying return format and null behavior. Every word earns its place.

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 simple read-only getter with one param and no output schema, the description covers purpose, parameter, return value, and null behavior. It does not mention error handling, but given the low complexity, it is complete.

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 has a single required id (string) with no description. The description adds that id is the 'file id (judgment DIS id)', clarifying the semantic type. It does not provide format examples, but this partial compensation is valuable given 0% schema coverage.

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?

Description clearly states it returns a plain-text judgment for a Hong Kong court file given a file id (DIS id). It distinguishes from siblings by specifying this is a document/judgment retrieval by id, unlike case retrieval (Hk_get_case) or listing (Hk_list_cases).

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?

No explicit comparison to sibling tools or when-not-to-use guidance. The intended use is implied: call this when you have a DIS id and need the judgment text. It does not clarify when to choose this over Hk_get_case or Hk_list_cases.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description does not need to restate safety. It adds behavioral value by specifying pagination and the response object shape ({data, total, page, limit}), plus substring semantics for partiesContains. No contradictions with 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 a single well-structured sentence followed by filter list and return shape, with no filler. It is front-loaded with the core function and immediately actionable.

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?

The tool has no output schema, so the description provides essential return-value information. It covers major filters and pagination, but omits details like filtering combination logic (AND/OR) and sorting, which are not critical for a straightforward list endpoint. Given annotations and sibling context, it is reasonably complete.

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?

With 0% schema description coverage, the description carries the full burden for parameter semantics. It explains case_prefix with examples, year, category, titleContains, and partiesContains (English or Chinese substring), but does not explicitly define page and limit, though 'paginated' and the response shape imply their role. Defaults are left to 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 clearly states the tool's function as providing paginated Hong Kong court cases, with actionable filters for case_prefix, year, category, titleContains, and partiesContains. This distinguishes it from sibling tools (Hk_get_case, Hk_get_document) by being a list/search operation rather than a single-case or document retrieval.

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 conveys a clear use case for listing and filtering court cases but does not explicitly mention when to use it instead of the sibling tools. It provides filter semantics and a return shape, establishing context for paginated queries, but lacks direct exclusionary guidance.

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