dataset_status

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

With no annotations, the description carries the burden and does well: it discloses that probe makes a live network round trip, reads only 2 KB, and is capped at 10 per call — the kind of cost/limit detail an agent needs before enabling it. It also flags a semantic trap (dct:modified is record revision date, not the statistical reference period). It stops short of describing failure behavior when a probe does not answer.

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?

Front-loaded with the core question, then structured into mode behavior and a distinct caveat paragraph. Every sentence carries information; only the question-form opener costs a little directness.

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?

An output schema exists so return values need not be explained, and the probe cost/cap and date-semantics caveat are covered. But one of four parameters (stale_after_days) is left completely undefined, which is a real gap for a tool whose central claim is judging staleness.

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 0%, so the description must compensate. It explains limit (the N oldest datasets), probe (live endpoint check with cost and cap), and the absence of dataset_id (list mode), but stale_after_days — which clearly drives the staleness verdict — is never mentioned anywhere.

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 rhetorical question is immediately grounded by concrete explanation: it reports whether datasets are still served and how stale they are, including a catalogue-listing mode. This is clearly distinguishable from catalogue-search or data-loading siblings such as search_hk_data and load_hk_data, though the opening framing is less direct than a verb+resource statement.

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?

It states the two usage modes explicitly: omit dataset_id to get a drift overview of the oldest datasets, or pass probe=True to actively verify the CSDI export endpoint answers. It does not name a sibling as an alternative, but the when-to-use context is clear enough to act on.

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