UK business finance reference data: Bank Rate history, R&D tribunal cases, invoice decline reasons.
Scored across 1 tool
With a single tool there is no tool-to-tool ambiguity, and the description clearly enumerates the four valid dataset names. The only fuzziness is that an agent must pick a dataset value with no listing/parameter schema to validate against, but the choices are spelled out explicitly.
There is only one tool, named in a clean snake_case verb_noun style that is fully consistent with itself. No mixed conventions are possible in a single-tool surface.
A single tool is thin for a server exposing four distinct datasets, each with different content and query semantics. It works because the datasets are enumerated in the description, but splitting per-dataset or adding a list-datasets tool would better fit the scope.
The tool covers read access to the stated reference datasets, which matches the server's read-only purpose. However there is no way to discover available datasets programmatically, no filtering/parameterization (dates, SIC codes, tribunal years), and no metadata or schema description beyond a one-line summary.
Return one dataset: "reference-data" (Bank Rate history, company size thresholds), "rd-tribunal-cases", "invoice-decline-reasons" or "sic-nec-tracker". Each file names its sources.
| Name | Required | Description | Default |
|---|---|---|---|
| dataset | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It discloses that the tool returns one dataset and that each file names its sources, but it does not state read-only status, side effects, permissions, output format, or rate limits.
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 front-loaded and compact: it states the return behavior, lists the choices, and adds a provenance note in two short sentences. There is no wasted wording.
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 one-parameter enum tool, the enumeration is enough to make a call mechanically possible. However, the description does not clarify what three of the four datasets contain and there is no output schema or return-format explanation, so an agent still lacks information needed to choose 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 exposes the four enum values with 0% description coverage. The description repeats those values and adds meaning only for "reference-data"; "rd-tribunal-cases", "invoice-decline-reasons", and "sic-nec-tracker" remain unexplained.
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 clear verb, "Return", and resource, "one dataset", and enumerates the four accepted dataset identifiers. It does not define the overall scope of "established finance data" beyond those names, but with no sibling tools there is no differentiation gap.
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?
There is no explicit when-to-use or when-not-to-use guidance, and no alternatives are named. The description only implies that the caller should choose one of the listed dataset values.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_established_finance_dataSourced, date-aware UK tax and payroll rates, deadlines and UK business checks, with GOV.UK sources.
UK specialty business finance lender terms and rates from the FundBiz Lender Index. Read-only.
Indicative UK lender criteria by borrower scenario, and Land Registry house prices by region.
UK company insolvency figures, winding-up petition counts and the insolvency practitioner register.
Add one secure layer between your agents and this server.