HKEx Filings

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses host rejection, truncation of document_text, a 30-table cap, and the extract=False behavior of returning only size/content-type, giving a clear picture of what happens when the tool is called.

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 short sentences with the main purpose front-loaded, followed by the most important constraint and the conditional response behavior. Every sentence adds necessary information and there is no filler.

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?

Given the tool's simplicity (2 parameters, one required), the description covers host validation, response content, and the extract switch. Since there is no output schema, the description sufficiently specifies return values so an agent can invoke the tool 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?

The schema already describes both parameters (100% coverage), and the description adds meaningful detail: the exact allowed host for link and the behavioral consequences of setting extract to true or false. This goes beyond the schema without needing to repeat basic parameter names.

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 precise action: download a single HKEx document by URL and extract its text and tables. This clearly differentiates the tool from siblings like get_server_info and search_filings, so an agent can tell which tool to invoke.

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 constraints: link must point to www1.hkexnews.hk and any other host is rejected. It also explains when to set extract=True vs extract=False, though it does not explicitly name alternative tools or say 'use search_filings first to find documents'.

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?

No annotations are present, so the description carries the behavioral burden. 'Reads nothing' explicitly discloses that the call has no side effects, and 'live' signals freshness. It does not cover failure modes or exact response format, but for a zero-parameter read-only info tool this is reasonable.

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 short sentences with zero filler. The core purpose is front-loaded and the safety note ('Reads nothing') is a single meaningful addition.

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 no-parameter info tool with unrelated siblings, the description is complete: it identifies what the tool reports and confirms it is read-only. No output schema exists, but the listed data categories are enough for an agent to interpret the result.

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?

The tool has zero parameters and schema coverage is effectively 100%, so there are no parameter semantics to explain. Baseline 4 for no-parameter tools applies; description adds no parameter info because none is needed.

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 uses a specific verb ('Report'), names the exact resource ('this live gateway'), and lists concrete data categories (version, transport, hard limits). It clearly distinguishes from the sibling filing tools by resource type.

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 the use case: call it when you need live gateway version, transport, or hard limits. It provides no explicit exclusions or alternative routing, but since siblings are unrelated filing tools, no when-not guidance is necessary.

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?

With no annotations, the description carries the full behavioral burden, and it delivers: it discloses the 31-day window limit, the hard cap of 200 on max_results, accepted date formats, and the return shape (parsed filings plus HKEx-reported total). These are non-obvious constraints an agent needs to call the tool correctly.

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 four tight sentences, front-loaded with the core operation and followed by parameter constraints and return behavior. Every sentence contributes necessary information, and backticks are used cleanly to reference parameter names.

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 four parameters, no annotations, and no output schema, this description is complete enough for an agent to invoke it correctly. It covers inputs, constraints, filtering behavior, and the return value, leaving no critical ambiguity.

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 75%, and the description compensates for the undocumented max_results by explaining it caps both fetching and returning with a hard cap of 200. It also clarifies stock_code filtering with concrete examples, adding meaning beyond the schema's generic 'Optional HKEx stock code'.

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 is specific: it names the verb 'Search', the resource 'live HKEx filings', and the key scoping dimension (date window). This naturally distinguishes it from siblings like get_filing, which fetches a single filing, and get_server_info, which is about server state.

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 clearly implies when to use the tool: to search filings by date, optionally filtered by stock code. However, it does not explicitly contrast with get_filing or state when one should prefer a sibling tool instead, so the guidance is implied rather than explicit.

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