Skip to main content
Open a workspace’s latest visibility changes, new citations, open work items, and due follow-ups. Call once at the start of any session about the brand’s site, content, SEO, or marketing. Returns brands, standingInstructions, brandContext, goals, open/due work, job results, moves, and account/low-credit alerts. Reading marks the brief read unless peek: true. Use brand to scope, moves: true for weekly movers, chains: true for workflow patterns, or view: “events” for the full paged event log. Free.

Who may call it, and what it costs

Price. Free. Every reply says what the call cost in meta.costCredits. The prices are on Spending, tracking and stopping.

Arguments

one of brief, events
brief (default): what passed the bar, ranked; events: every event
"last" or date or time
“last” (default: since the last brief) or an ISO date or time; with view: “events”, a day (UTC), in place of the last 7 days
date
events only: only events on or before this day (UTC)
list of one of changes, findings, pages, actions, rivals, jobs, account, nearby
default all up to 8
boolean
add the common jobs, each as its chain of calls (always added while the workspace has no brand)
boolean
add every brand of the workspace (its own and those it watches), each in its own markets, this week against the week before, largest move first, one read for all
string
the brd_ id of the brand this job is for, in a workspace that serves several (an agency’s clients): the brief is about it, nobody is asked which brand is theirs, and nothing is claimed or billed
boolean
read the brief without marking it read, so the next call (this key’s or another’s) still starts where the last read did
list of string
events only: only these kinds: mention_move, rival_move, finding, fact_contradicted, page_first_cited, page_dropped, page_changed, proof_step_blocked, own_page_changed, action_outcome, new_answer_batch, work_item, work_question, brief_delivered, job_finished, tracking_paused, budget_paused, auto_topup, auto_topup_failed, auto_topup_skipped, credits_expired, request_decided, setting_changed up to 20
integer
events only: default 25 min 1, max 200
string
events only: the page.cursor (an event id) to continue after
Every argument the tool takes, as GET /v1/tools serves it, every shared object written out; https://agent.parse.gl/openapi.json serves the same schema with the filter and the window named once under components and pointed to by $ref. MCP tools/list leaves out the arguments few calls send, and says the filter and the window once, under search_answers; resolve_ids {"kinds": ["argument"]} lists what it left out, and a call with any of them runs:

Example call

What changed for the workspace’s brands since the last brief. Over REST:
Over MCP, the assistant calls the tool by name with the same arguments:
More calls:
  • Every brand’s move this week against last, largest first: {"moves":true}
  • The brief for one client’s brand, in a workspace that serves several: {"brand":"<brd_ id>"}
  • Read the brief without marking it read for this key: {"peek":true}
  • Everything new in the workspace in the last 7 days, oldest first: {"view":"events","limit":20}
  • Only one brand’s events, between two days: {"view":"events","brand":"<brd_ id>","since":"2026-11-01","until":"2026-11-12"}
The reply has data, context, next, page and meta; follow next for the calls that come after. A refused call returns { code, message, fix }: see the error table.