Search the curated documentation catalog.

The catalog contains Strands Agents user guides, API reference pages, and examples. Ranking starts from document titles and also considers page content once a page has been fetched (hydrated), so both title-like keywords ("bedrock model", "MCP tools") and body terms ("guardrail", "temperature") work. The top results are fetched on demand to hydrate the index and provide content snippets.

Call fetch_doc with a result URL to read the page or one of its sections.

Args: query: Search query string (e.g., "bedrock model", "tell me about a2a", "how to use MCP tools") k: Maximum number of results to return (default: 5)

Returns: List of dictionaries containing: - url: Document URL - title: Display title - score: Unbounded weighted TF-IDF score. Higher is better within this result set; do not interpret it as a probability or compare it across different queries. - snippet: Contextual content preview

Returns an empty list when no document matches. If a result page
cannot be fetched, its title is used as the snippet.

Read documentation pages with smart sectioning for token efficiency.

Two modes of operation:

1. TOC mode (omit section): Returns a table of contents with section IDs, titles, summaries, and the document's preamble so you can decide which part to read.

2. Section mode (provide section): Returns the full markdown content of one section, identified by the ID from the TOC (e.g., "3" or "3.2").

For small documents (under ~8KB), the full content is returned directly regardless of mode, since sectioning would add overhead without benefit.

Recommended workflow:

1. search_docs("your query") - find relevant URLs

2. fetch_doc(uri="...") - see structure, preamble, and section summaries

3. fetch_doc(uri="...", section="3") - read the section you need

Args: uri: Document URL (must be under https://strandsagents.com/). If empty, returns a catalog of all available document URLs with titles. section: Section ID from the TOC (e.g., "3" or "3.2"). Omit to get the table of contents.

Returns: When section is omitted (TOC mode): - url, title: Document metadata - preamble: Introductory text between page title and first section - sections: List of sections with id, level, title, summary, children

When section is provided:
- url, title: Document metadata
- section_id: Requested section ID
- section_title: Section heading text
- content: Full markdown content of the section

For small documents (under ~8KB):
- url, title: Document metadata
- document_small: true
- content: Full document content (returned automatically)

On error:
- error: Error description
- url: Requested URL

Errors are returned for unsupported URLs and failed page fetches. For
sectioned documents, unknown section IDs also return an error; `section`
is ignored when the full document is returned automatically.