Regulatory search engine for EU textile sustainability law: ESPR, DPP, CSRD, CBAM, CWA 18291.
Scored across 8 tools
Most tools have clear, distinct roles: search vs. exact-text lookup, outline vs. fetch, and listing documents are well separated. The main ambiguity is between search and search_eu_textile_regulations, though the latter's regulatory scope is clearly stated; about_reecopedia also lacks a description but its name is self-explanatory.
All names are snake_caseión, but the style is mixed: bare verbs like fetch and search sit alongside verb_noun names like find_exact_text and list_corpus_documents, while document_outline and about_reecopedia don't follow the same verb pattern. The naming is readable but not predictable enough for a higher score.
Eight tools is well within the ideal range and each tool earns its place for a retrieval-focused corpus server: semantic search, exact-text search, document listing, outline navigation, fetching source text, and a feedback/reporting tool. No obvious bloat or unnecessary duplication.
The retrieval workflow is well covered: search discovers cited ids, fetch retrieves source text, find_exact_text handles literal lookup, and document_outline supports navigation; report_answer_issue closes the loop for quality feedback. Minor gaps exist such as no explicit document metadata tool or broader search scoping options, but agents can work around these.
Inputs: no named parameters. Returns: object
Return a compact navigation-v1 tree of indexed source text. Source metadata is shared in documents; depth/path encode hierarchy. Pass opaque ids unchanged to fetch. Warnings expose uncertain structure; citable=false marks navigation containers or unverified fragments.
Inputs: document (required). Returns: object
Fetch original text by an opaque id from search or document_outline. Pass ids unchanged. Navigation containers have citable=false and child ids, not source evidence. Historical page identifiers return migration guidance.
Inputs: id (required). Returns: object
Locate a literal string in the current corpus, optionally restricted to a document.
Inputs: text (required), document, max_results, case_sensitive. Returns: object
List indexed document names matching a substring.
Inputs: contains, max_results. Returns: object
File a report that an answer built from Reecopedia search results was wrong, misleading or incomplete. The report (the query and the reason, nothing else — no personal data) enters Reecopedia's human curation queue and is reviewed weekly to correct the corpus and retrieval quality.
THIS TOOL WRITES. Use it only when the user has asked for the problem to be reported, and send only the original query and the reason the user gave. Do not call it on your own initiative and do not add anything the user did not say.
ANNOTATIONS — why each hint is set the way it is, based on this tool's actual behaviour. readOnlyHint=false: this is the only tool that writes; it appends one record (the query and the reason, nothing else) to Reecopedia's internal human curation queue. destructiveHint=false: the write is append-only; it modifies and deletes nothing that already exists. idempotentHint=false: two calls can append two records — de-duplication covers only an identical query+reason pair within the same hour. openWorldHint=false: the record stays in the internal queue; it is not sent anywhere outside Reecopedia.
Inputs: query (required), reason (required). Returns: object
Return cited corpus results by id; use fetch for full source text. The client verifies the evidence. Query embeddings use Alibaba; candidate passages go to Jina for reranking.
Inputs: query (required). Returns: object
Search regulatory evidence in English legal register. Cite original document and unit; verify each claim. Optional scope narrows corpus partitions. No model assesses the answer in this MCP tool; the client must verify each claim against the returned text. Query embeddings use Alibaba; candidate passages are sent to Jina for reranking.
Inputs: query (required), scope, top_k. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
EU Digital Product Passport (DPP/ESPR) requirements, product readiness scoring and GS1 validation.
EU regulations (GDPR, DORA, NIS2, AI Act, etc.) via Ansvar Gateway. Cited, OAuth + paid.
Temporal search and comparison for official Luxembourg and reviewed EU law, with provenance.
EU law for AI: EUR-Lex legislation and case law, citation graph, semantic search with asOf.
Add one secure layer between your agents and this server.
