Tool Reference

Twenty tools in three groups. Most take a websiteId (from list_websites). The data tools share one time envelope: days for a trailing window or from + to for an explicit range, plus an optional segmentId to scope any read to one of the site's saved page-type segments.

Data reads

list_websites

Lists the websites your account can access, with their IDs. Start here.

get_schema

The site's data catalog: the complete query grammar with worked examples, the exact field names per grain, the site's custom extraction fields with live coverage, its saved segments, and the resolved date window. Call it before authoring queries - clients may truncate tool descriptions, but get_schema's grammar key is always complete.

query

The one structured read. Takes a JSON relation tree (ir) over five grains: per-URL on-page SEO, the raw bot request log, and Search Console per page, per query, and per-URL trend - with filters, aggregation, and joins between grains. Returns bounded rows with paging. See the query guide.

export

The same query IR, rendered to a downloadable CSV instead of bounded rows. query's row caps protect the conversation context; export is the way to hand over a full result set. Returns a download link when the file is ready.

path_tree

Orientation on the site's URL hierarchy: path sections with page counts and fetch activity. Useful as the first look at an unfamiliar site structure.

cannibalization_detail

Keywords where several of your URLs compete in search, with the competing URLs and their performance split per keyword.

query_alerts

The site's alert rules and their fired alerts.

read_page

The one live read: fetches a page's current content as markdown or HTML - for any domain, so competitor pages work too. For your own pages, pass CSS selectors to get just the matching elements. For a page's stored SEO detail as bots received it, use query on the on-page grain instead.

Keyword research

serp_check, ranked_keywords, keyword_expand, keyword_metrics, keyword_gap, find_competitors, backlink_summary.

Live SERP positions for chosen keywords; the keywords a domain ranks for; expansion of a seed keyword; search volume and difficulty metrics; the keyword gap against a competitor; competitor discovery; and a domain's backlink profile summary.

These tools buy live third-party data and draw on a daily per-site budget - use them deliberately rather than in loops. When the budget is exhausted, the tools say so and reset the next day.

Edge SEO authoring

Author on-page changes as draft rules from the conversation. The intended order:

1. read_page with selectors (or format: "html") - write CSS selectors against the page's real markup, not from memory.
2. preview_edge_seo_changes - dry-run the changes on top of the site's active ruleset and confirm they land where intended.
3. save_edge_seo_drafts - store the changes as a draft batch; returns a batchId.

Read back with list_edge_seo_rules (the active ruleset plus drafts) or get_edge_seo_draft_status (one batch by ID); discard a batch with delete_edge_seo_draft.

Drafts never go live from this surface: a human reviews and deploys them in the dashboard. There is deliberately no publish tool.