Search open UK public-sector tenders, government contracts, council & NHS procurement opportunities across Contracts Finder, Find a Tender, Scotland, Wales, Proactis & In-Tend. Free and no login required.
Scored across 3 tools
Each tool has a clearly distinct purpose: search_tenders finds tenders, get_tender fetches one by ID, and list_sources enumerates data sources. There is essentially no overlap; the search→get workflow is explicit.
All three tools follow a consistent snake_case verb_noun pattern (search_tenders, get_tender, list_sources). The convention is predictable and readable throughout.
Three tools are well-scoped for a focused tender-search service, each earning its place with a distinct function. It sits at the low end but is not thin enough to warrant penalty.
Core search → retrieve → source-listing is covered, but the 'Alert' branding implies subscription/notification or saved-search functionality that is entirely absent. There is also no filter-only or pagination tool beyond keyword search.
Get the full details of one UK tender by its ID (from search_tenders results): buyer, value, closing date, notice text and the link to the official notice.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The tender ID shown in search_tenders results. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent and non-destructive, so safety is covered structurally; the description adds value by listing the concrete fields the call surfaces, which the annotations cannot convey. It does not mention behavior for missing or stale IDs, which is the main remaining gap for a lookup-by-key tool.
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?
One sentence, front-loaded with the action and scope, then the payoff (returned fields). No redundant restatement of the title and no filler.
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 single-parameter read with no output schema, the description does the necessary extra work by enumerating the returned data, so an agent can judge whether the result answers its question. Combined with the annotations and fully documented schema, nothing essential 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 description coverage is 100% and the single 'id' parameter is already documented as 'The tender ID shown in search_tenders results'. The description's phrase 'by its ID (from search_tenders results)' restates that provenance rather than adding new meaning, so baseline 3 applies.
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?
States a specific verb and resource ('Get the full details of one UK tender by its ID') and enumerates what is returned (buyer, value, closing date, notice text, official notice link). This clearly distinguishes it from the sibling list/search tools, which return multiple tenders rather than one full record.
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 ties invocation to a prior step: the ID comes 'from search_tenders results', so the agent knows this is a follow-up detail call, not an entry point. It stops short of stating what to do when an ID is unknown or invalid, or when to prefer search_tenders alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the UK procurement sources Buzz Tender Alert covers, how many open tenders each currently has, and when the data was last refreshed.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the full safety profile (readOnlyHint, idempotentHint, non-destructive, closed-world), so the description is not obligated to cover that. It adds genuinely new context beyond annotations: the result includes a freshness timestamp and a live count of open tenders per source, which tells the agent the data is snapshot-like and time-sensitive rather than static.
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?
One sentence, front-loaded with the core action, and every clause adds distinct information (coverage set, per-source counts, freshness). No filler or restatement of the title.
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?
A zero-parameter, read-only catalogue call with no output schema is well served by a description that enumerates the returned fields, as this one does. Only minor gaps remain, such as result ordering or whether the list is exhaustive of all supported regions, neither of which is likely to change how the agent calls it.
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?
There are zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool applies. The description instead spends its words on what the call returns, which is the more useful information here.
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 names a specific verb ("List") and a specific resource ("UK procurement sources Buzz Tender Alert covers"), and it goes further by listing the per-source attributes returned: open tender counts and last refresh time. Siblings get_tender and search_tenders operate on tenders rather than on the source catalogue, so the resource distinction is unambiguous even without an explicit cross-reference.
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?
Usage is only implied: an agent can infer this is the discovery/coverage call you make before searching, but the description never states when to call it or points to search_tenders as the follow-up step. No exclusions or prerequisites are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search open UK public-sector tenders and procurement opportunities by keyword. Covers Contracts Finder, Find a Tender, Public Contracts Scotland, Sell2Wales, Proactis and In-Tend portals. Returns only tenders that are still open (closing date in the future, or not stated and recently published), most relevant first.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum results to return (default 10, max 25). | |
| query | Yes | Keywords to search for. All words must match. Supports "quoted phrases", OR between alternatives, and -word to exclude. Include a place or buyer name to narrow results, e.g. "grounds maintenance Hampshire" or "\"youth services\" OR \"young people\" -recruitment". | |
| source | No | Only return tenders from this source. | |
| closing_after | No | Only tenders closing on or after this date (YYYY-MM-DD), e.g. to leave time to prepare a bid. | |
| published_within_days | No | Only tenders published (or updated) in the last N days. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent and non-destructive, so the description's job is to add operational behaviour — which it does by disclosing the inclusion rule (only tenders still open, or unstated dates with recent publication) and the ranking order (most relevant first). It does not describe result shape or the practical effect of the limit cap, but the ranking and freshness rules are genuine added context.
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?
Three short sentences, front-loaded with the core action and scope, then coverage sources, then the filtering/ranking rule. No filler and nothing repeated.
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 five-parameter read-only search with a fully documented schema and no output schema, the description supplies the essentials: coverage, open-only constraint, and ordering. It leaves the per-result fields unspecified, which is a minor gap an agent would only notice after calling.
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%, with enum, pattern and range constraints already documented per parameter, so the schema carries the semantics. The description reinforces the source list and the open-only filter but adds no syntax or format detail beyond the schema — the correct baseline of 3.
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?
States a specific verb (search) plus resource (open UK public-sector tenders) and names the six portals covered, so an agent immediately knows this is a discovery tool rather than a single-record fetch like get_tender or a portal list like list_sources.
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?
Gives clear context for when the tool applies (keyword discovery of open opportunities) and implicitly scopes out awarded/closed tenders. It stops short of explicitly naming siblings or stating exclusions such as 'use get_tender once you have an ID', so it is clear but not fully routed.
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_tenderlist_sourcessearch_tenders
Add one secure layer between your agents and this server.