Conciseness

The body is dominated by lean, executable commands and tables, with only minor over-explanation such as the opening paragraph describing what CampaignHQ is ("CampaignHQ is a software platform used by political campaigns...") and flourishes like "so you can focus on the integration logic rather than auth plumbing". This fits anchor 4 ('efficient; minor instances of over-explanation that could be trimmed') rather than anchor 5's 'every token earns its place'.

Actionability

Guidance is fully executable and copy-paste ready: concrete install ("npm install -g @membranehq/cli@latest"), auth ("membrane login --tenant --clientName=<agentType>"), connection ("membrane connection ensure \"https://campaignhq.co/\" --json"), action execution with JSON input ("membrane action run <actionId> --connectionId=CONNECTION_ID --input '{\"key\": \"value\"}'"), and a flag table for proxy requests. Specific examples cover the common cases, matching anchor 5.

Workflow Clarity

The connection setup has a clear sequence with state-based checkpoints and a poll-again feedback loop ("poll again with membrane connection get <id> --json to check if the state moved to READY"), but the flow is broken by references to a nonexistent 'Step 2' ("If the returned connection has state: READY, skip to Step 2") and there is a '1b' heading with no '1a'. More importantly, destructive and send operations (delete-campaign, send-transactional-email) are listed with no validation or confirmation steps, which caps workflow clarity at 3 per the batch/destructive feedback-loop rule.

Progressive Disclosure

The document has good section structure but is a single monolithic file with a 20-row actions table inlined that functions as bulk API reference material ("## Popular actions" table) — content that belongs in a separate reference file per anchor 3 ('content that should be separate is inline'). It is not anchor 2 because sections are well-organized and commands are clearly presented, and not anchor 4 because there are no external reference files at all to offload detail.

Specificity

The description names the domain ("CampaignHQ integration") but its actions — "Manage data, records, and automate workflows" — are minimal and generic, with no concrete operations like managing donations, contacts, or campaigns. It matches the 'Names the domain but actions are minimal or generic' anchor rather than anchor 3, which requires 1-2 concrete actions.

Completeness

It answers both parts: what ("Manage data, records, and automate workflows") and an explicit when ("Use when the user wants to interact with CampaignHQ data"). Not anchor 5 because the 'what' is vague and the 'when' lacks concrete trigger phrases beyond CampaignHQ data; clearly above anchor 3, which requires a missing or weakly implied 'when'.

Trigger Term Quality

"CampaignHQ" is a strong, natural trigger term, but the remaining keywords ("data", "records", "workflows") are generic and miss common variations a user would actually say, such as donations, fundraising, contacts, volunteers, or mailing lists. This fits anchor 3 ('some relevant keywords but missing common variations or synonyms') better than anchor 4's 'good keyword coverage'.

Distinctiveness Conflict Risk

"CampaignHQ" is a specific named platform and the trigger clause is tied to it, giving a clear niche with distinct triggers and minimal conflict risk with other skills. The generic 'data' phrasing is subsumed by the explicit CampaignHQ scoping, so the anchor-5 example is the closest match.