recent_noticesList the most recent UK procurement notices from Contracts Finder, newest-first, optionally filtered by stage (tender/award). Same compact shape as search_notices. Keyless.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of recent notices to return, 1–100 (default 20). | |
| stage | No | Notice stage: "tender" or "award". Default "tender". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, openWorld, idempotent, non-destructive. The description adds useful context: 'Keyless' (no auth needed), 'newest-first' ordering, and 'same compact shape as search_notices' (consistent return format). No contradictions. Desc adds value beyond 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?
Two sentences, front-loaded with key action and source. No wasted words. Every sentence adds value: action, source, ordering, filter, shape, keyless.
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?
With no output schema, the description references 'same compact shape as search_notices' which delegates understanding. For a simple list tool with 2 params (optional), this is sufficient. However, it assumes knowledge of search_notices, leaving a minor gap. Overall, adequately complete.
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 baseline is 3. The description adds that 'newest-first' is the ordering, which is not in the schema, and clarifies the optional filter. This extra behavioral detail raises the score.
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 tool lists UK procurement notices from Contracts Finder, newest-first, with optional stage filtering. It also distinguishes itself by mentioning 'keyless' and 'same compact shape as search_notices', providing specific verb-resource-scope clarity.
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?
The description implies usage for retrieving recent notices with optional stage filter, but does not explicitly state when to use this versus siblings like 'search_notices' or 'find_a_tender_recent'. No when-not or alternatives are provided, only a mention of similarity to search_notices.
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.
Several tools occupy nearly identical roles (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools), and ask_pipeworx_beta is explicitly the same router as ask_pipeworx. Company-data tools (entity_profile, compare_entities, recent_changes, validate_claim) and the Polymarket family also overlap heavily, making selection error-prone despite detailed descriptions.
Tool names are consistently lowercase snake_case with a verb_noun pattern (search_notices, get_notice, find_a_tender_recent, validate_claim). Even longer names like polymarket_edge_tracker and ask_pipeworx_grounded follow a predictable style with no camelCase or mixed conventions.
36 tools is already excessive for a focused server, and the 'Uk Contracts' name covers only five of them (search_notices, recent_notices, get_notice, find_a_tender_recent, find_a_tender_notice). The remaining 31 are unrelated Pipeworx/Polymarket/AI-marketing utilities, so the count badly mismatches the apparent scope.
For UK public procurement, the five relevant tools provide search, recent listing, and full-detail retrieval for both Contracts Finder and Find a Tender Service, covering the core workflows well. Minor gaps include no tender-specific alert/subscription support and no server-side keyword search for the high-value FTS feed.