A
licenseNot graded
qualityC
maintenanceEnables restaurant owners to submit last night's close data and receive a prioritized, math-backed action for the next shift, along with limits and next steps.
MIT
Action Shift
Server Details
Free for restaurant owners. Drop last night's close, get the one thing to fix before next shift.
If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
A3.7/5.0
Scored across 1 tool
Disambiguation5/5
There is only one tool, so there is no possibility of confusing it with another. Its purpose (reading a restaurant close and producing a prioritized fix list) is stated explicitly and unambiguously.
Naming Consistency4/5
The single name action_shift_read_close is clear snake_case verb phrasing, so there is no inconsistency to penalize. The embedded server prefix is slightly redundant but still readable and predictable.
Tool Count3/5
A single tool is defensible given the narrow, deterministic read-only scope, but the surface feels thin for a named server ('Action Shift'). Users get exactly one operation with no alternatives or follow-ups.
Completeness3/5
The one tool covers its stated pipeline end-to-end (parse close numbers → owner desk line → next move), but the domain lacks any companion operations such as comparing closes across shifts or validating a pasted close. Agents hit a dead end after one call.
Available Tools
1 toolaction_shift_read_closeAction Shift: read last night's closeARead-onlyInspect
Read a restaurant close and return the Owner desk line, one Do this first finding, Not verified here, a 3-step next move, and at most 2 If time items, to fix before the next shift from numbers in a restaurant close (POS export, Z report, pasted text). Pass only numbers that appear in the close. Deterministic; no data stored.
| Name | Required | Description | Default |
|---|---|---|---|
| store | No | ||
| voids | No | ||
| payouts | No | ||
| discounts | No | ||
| grossSales | Yes | Sales for the shift/day from the close (required, > 0) | |
| orderCount | No | ||
| promotions | No | ||
| salesBasis | No | net, gross, or Subtotal, as labeled on the close | |
| businessDate | No | ||
| expectedCash | No | ||
| laborDollars | No | ||
| enteredDeposit | No | ||
| laborTargetPct | No | Operator's own labor % target. Never assume one. | |
| lateDeliveryCount | No | ||
| lateDeliverySales | No | ||
| targetDeliveryMinutes | No | ||
| averageDeliveryMinutes | No |
TDQS
A3.6/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds that the tool is deterministic and stores no data, and imposes an input constraint, which gives useful behavioral context beyond the annotations.
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?
Three sentences, front-loaded with the core action and output structure. The first sentence is dense with domain jargon but contains essential information; the other two add constraints efficiently. No filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 17-parameter tool with no output schema, the description outlines the return format at a high level and covers determinism/no-storage. However, it leaves most parameter semantics unexplained and doesn't fully specify the output structure, so it's only partially complete given the complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 18%, so the description must compensate, but it only offers the general instruction to pass numbers that appear in the close. It does not explain the meaning or role of the 16 optional parameters (voids, payouts, discounts, etc.), leaving their semantics largely undocumented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb and resource ('Read a restaurant close') and details the exact output shape (Owner desk line, Do this first finding, etc.), so an agent knows this is an analysis/synthesis tool rather than raw data retrieval. With no sibling tools, differentiation isn't needed, but the purpose is clear.
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?
It states the use case ('to fix before the next shift') and the input sources (POS export, Z report, pasted text), plus the constraint to pass only numbers that appear in the close. It doesn't provide explicit when-not guidance, but no alternatives exist.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- First observed
action_shift_read_close
Related MCP Connectors
Run your restaurant from an AI client: orders, menu, reports, refunds, payouts and staff.
Free restaurant profit check, recipe costing, calculators, website check, deadlines, guides, blog.
Plan shifts, cover sick days and check payroll for your restaurant, straight from the chat.
The brain for restaurant costs, pricing, and true profit (read/edit menu, recipes, costs).
Related MCP Servers
- FlicenseBqualityDmaintenanceEnables restaurant management through natural language, allowing import of Toast CSV data, labor/sales analysis, tip pool calculations, task management, and note-taking.14-
- AlicenseAqualityCmaintenanceProvides read-only access to daily trading figures for multi-site restaurant groups, detecting anomalies in control blocks such as void rates and labor percentages to uncover subtle financial leaks.5MIT
- AlicenseNot gradedqualityBmaintenanceProvides hospitality intelligence tools for restaurant optimization, including menu profitability analysis, food cost calculation, reservation management, review sentiment analysis, and allergen checking.6 npm37 PyPIMIT
Try in Browser
Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd
Glama MCP Gateway
Add one secure layer between your agents and this server.