# ARC (arcreport.ai): can an agent reach checkout? (ai.arcreport/ask): tool descriptions scored

- tools/list taken: 2026-11-02 (UTC)
- From: [Official MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/ai.arcreport%2Fask/versions/latest)
- Connected to: https://www.arcreport.ai/api/ask
- Homepage: https://www.arcreport.ai/for-agents
- Scoring rules: v2
- Tools: 17
- Average: 52.0 / 100 (Cloudy)
- Near-identical pairs: 0

This page shows how ARC (arcreport.ai): can an agent reach checkout? (ai.arcreport/ask)'s tool descriptions scored, the issues found and the names of its tools and parameters. The descriptions are the server's own: read them where the copy came from.

Forecall asked the URL this server lists in the official MCP Registry for its tools/list once, on the date above, without calling any tool. The server may have changed since.

## Across the server

- Minor: The server's instructions are 3804 characters. Claude Code reads only the first 2,048 by default (Codex 0.154.0 reads them whole). Put what the server is for first.

## Tools

- `submit_store`: 34 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: url, hosts, category.
  - Minor: String arguments with no constraint or example: url.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
- `product_data_check`: 36 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Major: Arguments without a description: host, url.
  - Minor: String arguments with no constraint or example: host, url.
  - Minor: No `required` list, so every argument is optional.
- `google_checkout_readiness`: 38 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `list_category_agent_facts`: 40 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `get_agent_facts`: 47 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No `required` list, so every argument is optional.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `agent_leaderboard`: 49 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
- `dataset_info`: 49 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
- `protocol_matrix`: 49 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
- `store_card`: 50 / 100
  - Minor: Says nothing about what it returns.
- `agent_commerce_adoption`: 52 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: Says nothing about what it returns.
- `submit_leaderboard_run`: 53 / 100
  - Major: Arguments without a description: spec, test_set, agent, agent.name, agent.version, agent.builder, agent.path, agent.model, run, run.stopped_before_payment, run.notes, results, results[].outcome, results[].at, results[].evidence_url, results[].steps, results[].seconds.
  - Minor: String arguments with no constraint or example: spec, test_set, run.started_at, run.finished_at, results[].at, results[].evidence_url.
  - Minor: The meaning of the boolean argument run.stopped_before_payment is unclear.
  - Minor: Says nothing about what it returns.
- `find_agent_ready_stores`: 54 / 100
  - Minor: Arguments without a description: limit.
  - Minor: No `required` list, so every argument is optional.
  - Minor: Says nothing about what it returns.
- `validate_ucp_profile`: 57 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: No `required` list, so every argument is optional.
- `ask_arc`: 62 / 100
  - Minor: No `required` list, so every argument is optional.
  - Minor: No constraints, side effects, auth or rate limits described, and no annotations.
- `can_agent_checkout`: 66 / 100
- `precheck_bulk`: 69 / 100
  - Major: Says nothing about when to use it, or when not to.
- `precheck`: 79 / 100

Is your server listed here and you would rather it were not? Email support@forecall.dev, and we will take it off within 7 days.

[All scored servers](https://forecall.dev/en/servers)