Reecopedia

Search EU textile regulations

search_eu_textile_regulations

Read-only

LANGUAGE CONTRACT — READ BEFORE CALLING. Corpus is English. Call this tool ONLY with an English query in the legal register of the act (the wording of the Official Journal), not a tourist translation. Keep act identifiers and rewrite article/annex numbers into English (Article 9, Annex I; 第9条 / Artikel 9 / articolo 9 → Article 9). After you receive passages, answer the user in the user's language; quote the law in English with (file, page, article). If the user spoke another language, YOU translate before this call. Do not send non-English text in query.

Primary question-answering search over the Reecopedia corpus of EU textile sustainability regulations. Use this for natural-language regulatory questions.

Returns the most relevant passages with citations (source file, page, section); answer ONLY from these passages and cite them. Corpus: ESPR 2024/1781, Digital Product Passport, CSRD, CBAM, EU ETS, CWA 18291, JRC BREF and textile preparatory studies, EP studies.

For a browsable result list instead of an answer, use search.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes	ENGLISH ONLY, in the legal register of the act. A non-English `query` violates this tool's contract and its passages must be discarded, not answered from. Act identifiers stay verbatim ("ESPR", "2024/1781"): they are matched as metadata. Article and annex numbers must be rewritten into their English form, because that is how they are matched: "第9条" and "Artikel 9" do not match, "Article 9" does. Measured 2026-08-27 on the live index, one question three ways: "must a marketplace show the product passport before purchase, where is it written?" returned NOTHING; "marketplace must make the digital product passport accessible before purchase" returned the CWA guidance (0.96) with the ESPR at 0.001; "make the digital product passport accessible to customers before they are bound by a contract of sale" returned the ESPR itself first (0.94, p.21).
`top_k`	No	Number of passages to return (1-10, default 10).

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already mark the tool read-only and non-destructive, but the description adds important behavioral detail: English-only querying, citations in a specific format, answering only from retrieved passages, and discarding non-English query results. No contradiction with the annotations was found.

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

Conciseness5/5

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

The description is front-loaded with the critical language contract, then gives the tool's purpose, return behavior, corpus scope, and sibling alternative. Every block adds necessary invocation guidance, and even the longer language-contract section earns its place.

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?

Given the output schema, read-only annotations, and tool complexity, the description covers everything needed: query language constraints, translation behavior, citation format, answer grounding, corpus coverage, and when to use a sibling tool. No critical gap is apparent.

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

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the input schema's `query` description already covers English-only input, legal-register wording, and Article/Annex number rewriting. The description reinforces these points and adds the translate-before-call instruction, but the schema carries most of the parameter-semantics burden.

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 precise question-answering search over the Reecopedia EU textile corpus, not just 'search EU textile regulations'. It explicitly differentiates itself from `search` by describing its answer-oriented behavior and by naming the browsable-list alternative.

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?

Explicitly says to use this tool for natural-language regulatory questions and routes browsable-result needs to `search`. It also sets clear preconditions: the query must be in English and in the legal register of the act, and the agent must translate before calling when the user speaks another language.

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

All Reecopedia tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0

Disambiguation4/5

Most tools have clearly distinct purposes: semantic answering, browsable search, exact-string lookup, outline navigation, full-page fetch, about, and feedback. The main ambiguity is between `search` and `search_eu_textile_regulations`, but their descriptions do separate result-list browsing from cited passage answers.

Naming Consistency3/5

All names use lowercase snake_case, but the pattern is mixed: `fetch` and `search` are one-word verbs, `document_outline` is a noun compound, `about_reecopedia` begins with a preposition, and the rest use verb_object naming. The inconsistency is readable but not predictable enough to infer tool behavior from names alone.

Tool Count5/5

Seven tools is a well-scoped size for a specialized regulatory-corpus reader: Q&A, browse, exact search, outline, fetch, about, and feedback each earn their place. There is no redundancy or bloated surface.

Completeness5/5

The toolset covers the full retrieval lifecycle: ask a regulatory question, browse results, find exact strings, inspect document structure, fetch full pages, and report bad answers for curation. No obvious dead ends or missing operations are apparent for the stated domain.

Resources

Need Help?