RTFD (Read The F*****g Docs)

Instructions

Implementation Reference

• src/RTFD/providers/zig.py:41-70 (handler)

  The main zig_docs tool handler: async function that takes a query string, calls the private _search_zig_docs helper, and serializes the result into CallToolResult using serialize_response_with_meta.
  async def zig_docs(query: str) -> CallToolResult: """ Search Zig programming language documentation. USE THIS WHEN: You need information about Zig language features, syntax, stdlib, or concepts. BEST FOR: Learning Zig language specifics and finding relevant documentation sections. Searches the official Zig documentation (ziglang.org/documentation/master/) and returns matching sections with titles, summaries, and relevance scores. Good for queries about: - Language features (e.g., "comptime", "async", "optionals") - Standard library (e.g., "ArrayList", "HashMap", "allocators") - Memory management (e.g., "allocator", "defer", "errdefer") - Error handling (e.g., "error sets", "try", "catch") - Build system (e.g., "build.zig", "zig build") NOT SUITABLE FOR: Third-party Zig packages (use GitHub provider for that) Args: query: Search keywords (e.g., "comptime", "async", "ArrayList", "error handling") Returns: JSON with matching documentation sections, relevance scores, and source URL Example: zig_docs("comptime") → Returns sections about compile-time code execution """ result = await self._search_zig_docs(query) return serialize_response_with_meta(result)
• src/RTFD/providers/zig.py:19-28 (registration)

  Registration in provider metadata: declares tool_names=["zig_docs"] in get_metadata().
  def get_metadata(self) -> ProviderMetadata: return ProviderMetadata( name="zig", description="Zig programming language documentation", expose_as_tool=True, tool_names=["zig_docs"], supports_library_search=False, # Zig docs are not a library/package search required_env_vars=[], optional_env_vars=[], )
• src/RTFD/providers/zig.py:38-71 (registration)

  Registration of the tool function: defines and returns {"zig_docs": zig_docs} in get_tools().
  def get_tools(self) -> dict[str, Callable]: """Return MCP tool functions.""" async def zig_docs(query: str) -> CallToolResult: """ Search Zig programming language documentation. USE THIS WHEN: You need information about Zig language features, syntax, stdlib, or concepts. BEST FOR: Learning Zig language specifics and finding relevant documentation sections. Searches the official Zig documentation (ziglang.org/documentation/master/) and returns matching sections with titles, summaries, and relevance scores. Good for queries about: - Language features (e.g., "comptime", "async", "optionals") - Standard library (e.g., "ArrayList", "HashMap", "allocators") - Memory management (e.g., "allocator", "defer", "errdefer") - Error handling (e.g., "error sets", "try", "catch") - Build system (e.g., "build.zig", "zig build") NOT SUITABLE FOR: Third-party Zig packages (use GitHub provider for that) Args: query: Search keywords (e.g., "comptime", "async", "ArrayList", "error handling") Returns: JSON with matching documentation sections, relevance scores, and source URL Example: zig_docs("comptime") → Returns sections about compile-time code execution """ result = await self._search_zig_docs(query) return serialize_response_with_meta(result) return {"zig_docs": zig_docs}
• src/RTFD/providers/zig.py:73-107 (helper)

  Core helper _search_zig_docs: fetches Zig docs from https://ziglang.org/documentation/master/, extracts sections, searches for query matches, returns structured results with relevance scores.
  async def _search_zig_docs(self, query: str) -> dict[str, Any]: """Search Zig documentation and return relevant sections.""" try: # Fetch the master documentation page url = "https://ziglang.org/documentation/master/" async with await self._http_client() as client: resp = await client.get(url, follow_redirects=True) resp.raise_for_status() soup = BeautifulSoup(resp.text, "html.parser") # Build a search index of documentation sections sections = self._extract_doc_sections(soup) # Find matching sections based on query matches = self._search_sections(sections, query.lower()) return { "query": query, "source": "https://ziglang.org/documentation/master/", "matches": matches[:5], # Limit to top 5 results "total_matches": len(matches), } except httpx.HTTPError as exc: return { "query": query, "error": f"Failed to fetch Zig documentation: {exc}", "source": "https://ziglang.org/documentation/master/", } except Exception as exc: return { "query": query, "error": f"Error searching Zig documentation: {exc}", "source": "https://ziglang.org/documentation/master/", }
• src/RTFD/providers/zig.py:145-173 (helper)

  Helper _search_sections: scores documentation sections based on query word matches in title and summary, sorts by relevance.
  def _search_sections(self, sections: list[dict[str, str]], query: str) -> list[dict[str, Any]]: """Search sections for matches based on query string.""" matches = [] query_words = query.lower().split() for section in sections: title_lower = section["title"].lower() summary_lower = section["summary"].lower() # Score based on word matches (individual words from query) total_score = 0 for word in query_words: # Title matches are weighted higher title_score = title_lower.count(word) summary_score = summary_lower.count(word) total_score += (title_score * 2) + summary_score if total_score > 0: matches.append( { "title": section["title"], "summary": section["summary"], "relevance_score": total_score, } ) # Sort by relevance score matches.sort(key=lambda x: x["relevance_score"], reverse=True) return matches