Conciseness

The body is mostly efficient, command-driven content, but contains removable padding: the 'Clientary Overview' bullet list with duplicate '**Note**' entries, the filler sentence 'Use action names and parameters as needed.', and the rambling 'Agent Types' paragraph ('etc. Those will be used to adjust tooling to be used best with your harness'). It fits 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than level 4, since several sections are pure overhead.

Actionability

Concrete, executable commands appear throughout: install (`npm install -g @membranehq/cli@latest`), login including headless completion, `membrane connection ensure`, polling with `--wait`, `action list --intent`, `action run --input`, and a proxy flag table. It fits 'mostly executable guidance; concrete code or commands with minor gaps' rather than level 5, since placeholders like CONNECTION_ID and <actionId> are never resolved in a worked end-to-end example.

Workflow Clarity

The sequence (install → login → connect → poll state → search actions → run → proxy fallback) is clear, with explicit state-machine checkpoints (READY / BUILDING / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) and a poll-again feedback loop after user actions. Not level 5: 'Skip to **Step 2**' is referenced twice but no Step 2 (or Step 1) exists in the document, and no error handling is given for failed action runs.

Progressive Disclosure

The document has good structure with clear section headers, well-organized command examples, and an inline popular-actions table that is appropriately sized to stay in the main file. It fits 'good structure; most content is appropriately placed' rather than level 5 because there are no bundle files at all, so all detail (overview bullets, proxy flag table) is inline in a >50-line document with no one-level-deep reference structure.

Specificity

The description names the domain ('Clientary integration') but its actions are entirely generic ('Manage data, records, and automate workflows') with no concrete capabilities like clients, projects, invoices, or time tracking. It matches the anchor 'names the domain but actions are minimal or generic' rather than level 3, which requires at least one concrete action.

Completeness

Both a what ('Manage data, records, and automate workflows') and an explicit when ('Use when the user wants to interact with Clientary data') are present, so the cap-3 rule for missing trigger guidance does not apply. Not level 5 because the 'what' is generic and the 'when' could name concrete trigger phrases.

Trigger Term Quality

'Clientary' is the natural keyword a user would say and is present, but the description omits common variations and synonyms users would actually use (CRM, invoicing, clients, projects, estimates, time tracking). This is 'some relevant keywords but missing common variations or synonyms', not level 4, since coverage beyond the app name is thin.

Distinctiveness Conflict Risk

Naming the niche app Clientary makes it mostly distinct with minimal conflict risk, but the generic phrase 'Manage data, records, and automate workflows' could overlap with other data-management or integration skills. Not level 5 because the description's distinctiveness rests solely on the app name.