Skip to main content
Glama
Sign In
UnClick MCP Server

UnClick MCP Server

by malamutemayhem
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

uxpass_run

Run a synchronous UX journey/usability check on a URL or registered pack, returning run ID, status, UX Score, summary, and receipt. Use task_id to make retries idempotent and avoid duplicate runs.

Instructions

Run a UX journey/usability check synchronously against a URL. Executes the deterministic uxpass-core check set and returns the run id, status, UX Score, summary, and uxpass_receipt_v1. UIPass now owns visual/interface polish; this legacy UXPass runner still calls out when screenshots or mobile/desktop proof are missing for visible surfaces. Pass either url (a one-off check) or pack_name (resolves the registered pack's url). The hats parameter is accepted for forward compatibility but is currently ignored; LLM hats land in a later chunk. Response includes was_duplicate: boolean indicating whether the row was already present (idempotent retry).

Input Schema

NameRequiredDescriptionDefault
urlNoTarget URL for a one-off run (takes precedence over pack_name)
hatsNoReserved for future use. Currently ignored; the deterministic runner evaluates the full uxpass-core check set on every run.
task_idNoClient-generated idempotency key (UUIDv5 from thread_id + prompt_hash + time_bucket recommended). Required for safe retry. If omitted, the server creates a fresh row and you lose retry safety; sending the same task_id twice returns the original run_id with was_duplicate=true instead of creating a duplicate.
pack_nameNoName of a registered UXPass pack; the pack's url is used as the target
target_shaNoOptional PR or commit SHA for receipt staleness checks.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.11
    • addedInput schema / properties / target_sha
      Added value: +{
+  "description": "Optional PR or commit SHA for receipt staleness checks.",
+  "type": "string"
+}
  2. Addedv0.1.9
  3. Removed
  4. Addedv0.1.5

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: synchronous execution, the returned fields, the was_duplicate idempotency behavior, the retry-safety role of task_id, and the fact that hats is silently ignored for forward compatibility. Auth requirements and rate limits are still unstated, keeping it below a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core action and keeps each sentence functional (scope, precedence, ignored param, idempotency), though a couple of clauses about UIPass ownership and 'LLM hats land in a later chunk' are more lore than actionable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Since no output schema exists, the description usefully enumerates the response (run id, status, UX Score, summary, uxpass_receipt_v1, was_duplicate) and covers both target inputs and idempotency. Complete enough to call correctly, with only auth/limits and receipt structure left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents url precedence, the ignored hats array, the task_id idempotency key and target_sha. The description restates the same semantics rather than adding new detail, which is the baseline 3 case.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run a UX journey/usability check synchronously against a URL') and names the deterministic uxpass-core check set and the returned artifacts. It is readily distinguishable from uxpass_status, uxpass_report_* and uxpass_register_pack without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains the url-vs-pack_name selection rule and clarifies the tool's scope relative to UIPass ('UIPass now owns visual/interface polish; this legacy runner still calls out missing screenshot/mobile proof'). It does not explicitly point to sibling tools such as uxpass_status for polling, so it stops short of full when/when-not/alternatives guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools