UK GCSE and A-level exam dates, results days, entry deadlines and spec changes.
Scored across 1 tool
There is only a single tool, so there is no possibility of an agent confusing it with another tool. Its purpose (retrieving UK exam calendar data by kind, board, and qualification) is clearly stated.
With just one tool named uk_exam_dates in snake_case, there are no competing conventions to clash. The name is readable and matches the server's domain.
A single tool is borderline thin for a server whose surface spans results days, timetables, entry deadlines, and specification changes. It works as a parameterized lookup, but a slightly richer surface could better express the distinct query categories.
The tool covers the main categories of the domain (results, timetable, deadlines, spec changes) with per-board and per-qualification granularity, plus explicit handling of unknown inputs. Coverage is strong, though packing everything into one kind parameter means no dedicated operations for narrower sub-queries.
UK exam calendar dates verified against JCQ and the exam boards' own documents: results days (A-level 12 August 2027, GCSE 19 August 2027, November 2026 GCSE resits 13 January 2027, Scotland 10 August 2027), the summer 2027 exam timetable (JCQ common window 10 May – 22 June, contingency day 23 June 2027; per board — AQA, Pearson Edexcel, Cambridge OCR and WJEC/Eduqas, all final — the dates of GCSE Maths papers 1–3, English Language papers 1–2, Combined Science papers and A-level Maths papers), entry deadlines (JCQ 21 February 2027) with each board's late and very-late entry fee dates and multipliers, and announced specification changes (first-teaching and first-exam years, DfE reform timetable, Ofqual decisions). Input kind (results, timetable, deadlines, spec-changes; omitted → the listing), optional board (jcq, aqa, pearson/edexcel, ocr, wjec/eduqas, sqa, ofqual, dfe) and qualification (gcse, a-level). Every figure carries its source document, the quoted timetable row, verifiedDate (2026-10-04) and, where the board's 2026 document is still served, the summer-2026 date as previous. An unknown kind, board or qualification answers covered:false with the nearest keys.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | one of: results, timetable, deadlines, spec-changes (omit to list all) | |
| board | No | optional: jcq (common dates), aqa, pearson (edexcel), ocr (cambridge), wjec-eduqas (wjec, eduqas), sqa (Scotland), ofqual, dfe | |
| qualification | No | optional: gcse or a-level (figures common to both are returned for either) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare read-only/idempotent safety attributes, so the description must carry the return-shape burden and it does: every figure carries its source document, quoted timetable row, verifiedDate, and previous-year date where available. It also discloses the miss behavior (covered:false with nearest keys), which is genuine behavioral context beyond the 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?
It is long and delivered as a single dense paragraph, which hurts scanning, but the opening sentence front-loads the scope and almost every clause earns its place by defining precise coverage (dates, timetable window, contingency day, late-entry multipliers). The enumeration of specific calendar dates is borderline payload-in-description, keeping it from a 5.
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?
There is no output schema and no annotation coverage of return structure, so the description must explain what comes back — and it does, including per-figure provenance fields, the quoted source row, verifiedDate, and the previous-year fallback. Nothing needed to invoke or interpret the result is missing.
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 coverage is 100% so the baseline is 3, but the description adds real meaning beyond the schema: omission of kind defaults to the listing, board values are given as aliases (pearson/edexcel, wjec/eduqas), and qualification is explained as returning figures common to both when either value is supplied.
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?
Names the specific resource (UK exam calendar dates) and enumerates precisely which categories it covers: results days, summer 2027 timetable, entry deadlines, and specification changes, with named sources (JCQ, AQA, Pearson Edexcel, OCR, WJEC/Eduqas, SQA, Ofqual, DfE). An agent knows exactly what this tool returns without guessing.
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?
Explicitly states the accepted input kinds, that omitting kind returns the listing, and that an unknown kind/board/qualification yields covered:false with nearest keys. There are no sibling tools to route against, so the conditional behavior is the only usage guidance needed, and it is stated clearly.
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.
uk_exam_datesUK exam-board spec data: which paper is a topic on, spec structures, past-paper links. Verified.
UK and Ireland public sector tenders, contract awards, buyers and expected re-tenders.
UK & EU tenders, awards, planning, companies, charities, schools, NHS, care, gambling, trade marks.
UK government service fees, steps, processing times and recent changes, read from gov.uk.
Add one secure layer between your agents and this server.