Skip to main content
Glama
Sign In

Uk Contracts

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Find A Tender Recent

find_a_tender_recent
Read-onlyIdempotent

Recent OR HISTORICAL high-value UK government tenders and contract awards from the Find a Tender Service (find-tender.service.gov.uk) — the UK's above-threshold procurement portal (the post-Brexit replacement for EU TED, for larger public contracts). Use for "high value UK tenders", "above threshold UK government contracts", "Find a Tender notices", "large UK public sector contract opportunities", or a historical window like "FTS notices from 2023". Returns notices newest-first within the window days reaches back. An optional keyword is matched over title, description, award title and AWARDED SUPPLIER — client-side, because the FTS API has no text search (it rejects a keyword parameter outright, allowing only stages/limit/cursor/updatedFrom/updatedTo). ALWAYS READ window_complete: false means the walk stopped at the page cap (8 pages/call) with more feed left, so a zero means "absent from the notices examined", not "not published" — narrow days or stage until it is true, or repeat the call from where it stopped. For a proper full-corpus keyword SEARCH of UK procurement with real historical date filtering (not just a bounded walk), and for lower-value notices, use search_notices (Contracts Finder), which does have a real server-side index. Keyless.

Input Schema

NameRequiredDescriptionDefault
daysNoHow many days back to scan, 1–3660 (~10 years; FTS itself accepts any historical date, verified live). Default 7 when listing, 30 when a keyword is given (the 7-day feed is only ~30 notices, too few for a keyword to match). A wide window still walks at most 8 pages per call (see window_complete) — narrow with stage/keyword for a window the walk can finish in one call.
limitNoMax notices to return, 1–100 (default 20).
stageNoNotice stage: "tender" (open opportunities, default), "award" (results), or "planning".
keywordNoOptional keyword to filter recent notices by title/description, e.g. "cloud", "construction". Omit to list all recent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "days": 7,
-    "limit": 20,
-    "stage": "tender"
-  },
-  {
-    "days": 30,
-    "keyword": "MRI",
-    "stage": "tender"
-  },
-  {
-    "days": 3,
-    "keyword": "MRI",
-    "stage": "award"
-  }
-]New value: +[
+  {
+    "days": 7,
+    "limit": 20,
+    "stage": "tender"
+  },
+  {
+    "days": 30,
+    "keyword": "MRI",
+    "stage": "tender"
+  },
+  {
+    "days": 3,
+    "keyword": "MRI",
+    "stage": "award"
+  },
+  {
+    "days": 400,
+    "stage": "award"
+  }
+]
    • changedInput schema / properties / days / description
      Previous value: -"How many days back to scan, 1–30. Default 7 when listing, 30 when a keyword is given (the 7-day feed is only ~30 notices, too few for a keyword to match)."New value: +"How many days back to scan, 1–3660 (~10 years; FTS itself accepts any historical date, verified live). Default 7 when listing, 30 when a keyword is given (the 7-day feed is only ~30 notices, too few for a keyword to match). A wide window still walks at most 8 pages per call (see window_complete) — narrow with stage/keyword for a window the walk can finish in one call."
  2. Changed1 schema field changed
    • changedInput schema / properties / days / description
      Previous value: -"How many days back to scan, 1–30 (default 7)."New value: +"How many days back to scan, 1–30. Default 7 when listing, 30 when a keyword is given (the 7-day feed is only ~30 notices, too few for a keyword to match)."
  3. Changed1 schema field changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "days": 7,
-    "limit": 20,
-    "stage": "tender"
-  },
-  {
-    "days": 14,
-    "keyword": "construction",
-    "limit": 30,
-    "stage": "award"
-  }
-]New value: +[
+  {
+    "days": 7,
+    "limit": 20,
+    "stage": "tender"
+  },
+  {
+    "days": 30,
+    "keyword": "MRI",
+    "stage": "tender"
+  },
+  {
+    "days": 3,
+    "keyword": "MRI",
+    "stage": "award"
+  }
+]
  4. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "days": 7,
+    "limit": 20,
+    "stage": "tender"
+  },
+  {
+    "days": 14,
+    "keyword": "construction",
+    "limit": 30,
+    "stage": "award"
+  }
+]
  5. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnly/idempotent/openWorld; the description adds far more: keyword matching is client-side because the FTS API rejects a keyword parameter, the 8-page-per-call walk cap, the critical window_complete flag semantics (false = truncated, so zero is inconclusive), and how to narrow days/stage to finish the walk. These are non-obvious behaviors an agent must know to interpret results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and trigger phrases, then the operational caveats; nearly every sentence carries unique information. It is dense and long, with minor overlap between the description and schema text on days/limit defaults, but nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description still documents the one return-field an agent must interpret (window_complete) and the ordering (newest-first within days). Combined with the documented page cap and keyword caveat, an agent has everything needed to call and correctly interpret this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

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 meaning beyond the schema: it clarifies that keyword is matched over award title and AWARDED SUPPLIER in addition to title/description, and explains why days defaults differ (7 vs 30 with keyword) and how wide windows interact with the page cap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (fetch recent/historical UK high-value tenders and contract awards from Find a Tender Service) and names the exact source portal. It explicitly distinguishes itself from sibling search_notices and clarifies the value tier (above-threshold, high-value) versus lower-value notices, so an agent can route without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete trigger phrases ("high value UK tenders", "above threshold UK government contracts", historical windows like "FTS notices from 2023") and explicitly names the alternative: use search_notices (Contracts Finder) for full-corpus keyword search, real historical date filtering, and lower-value notices. When-to-use and when-to-switch are both spelled out.

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

All Uk Contracts toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources