Fetch a STORED table whole, by dataset id (families cn-nbs-census and cn-nbs-yearbook): labelled rows × columns with original-language labels, English overlay, units, and provenance down to the source file. Ids look like 'cn-nbs-census:2010_a0101a'.
| Name | Required | Description | Default |
|---|---|---|---|
| dataset_id | Yes | catalog dataset id |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the disclosure burden. It clearly states this is a fetch operation (non-mutating) that returns the whole stored table, and describes the content structure. It does not mention error handling or potential limitations, but given the simplicity, the core behavioral traits are disclosed.
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 that front-loads the core action ('Fetch a STORED table whole'), then details the return contents and ID format. No wasted words; every phrase 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 tool with one parameter and no output schema, the description fully covers what the agent needs to know: what it retrieves, the exact input format, and the families involved. There is no missing operational detail that would prevent correct usage.
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 dataset_id as 'catalog dataset id' (100% coverage). The description adds significant value by giving the exact ID format ('cn-nbs-census:2010_a0101a') and the applicable families, which helps the agent construct valid values. This goes beyond the schema's minimal description.
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 verb 'Fetch', the resource (a STORED table), and the distinguishing scope (by dataset id, with families cn-nbs-census and cn-nbs-yearbook). It also specifies the exact return contents (labelled rows×columns, labels, English overlay, units, provenance), which differentiates it from siblings like tariff_lookup or resolve_data.
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 implies usage when you have a dataset_id and provides the ID format, but it does not explicitly state when to prefer this over search_datasets (e.g., when you already have an ID) or exclude scenarios like searching by keyword. The guidance is implied but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct operation: catalog search, exact table retrieval, natural-language data resolution, and tariff lookup. Even though search and resolve both accept English queries, one returns dataset IDs and the other returns observations, so the boundaries are clear.
Three tools follow a clear verb_noun pattern (get_table, resolve_data, search_datasets), and all names use lowercase snake_case. tariff_lookup deviates slightly from the verb-first pattern but remains consistent in style and readable.
Four tools is a well-scoped count for a read-only statistical data server. Each tool provides a distinct core capability with no redundant or filler tools.
The core read-only data workflow is covered: discover dataset IDs, fetch a known table, ask a data question, and run tariff lookups. Minor gaps such as schema-only metadata access or generic table filtering are not present, but agents can work around them with the existing tools.