Ask Claude "Did anyone miss a meal break last Tuesday?" — and have it actually be right.
Every HR / payroll / time-tracking team eventually asks Claude (or Cursor, or Windsurf) something like:
"Rahim's punches yesterday were 09:00, 13:00, 14:00, and 18:00. Did he get his meal break under California rules?"
And the LLM does what LLMs do: it eyeballs the timestamps, mumbles something about "yes probably, his lunch looks fine," and moves on. Sometimes it's right. Sometimes it forgets that California requires the meal to start before the end of the 5th hour. Sometimes it counts a 25-minute break as compliant. Sometimes, for an overnight shift that crosses midnight, it just gives up.
You can't put that in front of an auditor. You can't ship it inside a payroll product. You can't trust it with overtime calculations that turn into back-pay liability if they're wrong.
Related MCP server: TimeIQ MCP Server
A small Model Context Protocol server that gives your AI agent deterministic, tested, fixture-backed tools for:
Resolving a duty day from raw clock punches (overnight, breaks, OT, all of it).
Auditing meal/rest compliance under the California rule pack (Labor Code §§ 226.7, 512; IWC wage orders), including Donohue v. AMN rebuttable-presumption signals.
Rounding worked time without losing the exact-minute baseline (so you can prove your rounding is neutral).
Building rotating rosters: 2-2-3, 4-on-4-off, DuPont, Pitman.
Triaging suspicious punch streams before you trust them.
Running a multi-day wage-and-hour audit across a whole pay period and rolling up premium hours owed, days at risk, and the flag heatmap.
The math lives in @attendance-engine/core — a pure-function, zero-deps TypeScript library with 100% test coverage. This MCP server is the thin agent surface on top.
flowchart LR
A[You: "Did Rahim miss his meal break last Tuesday?"]
B[Claude / Cursor / Windsurf]
C[attendance-engine MCP]
D[("@attendance-engine/core
pure-function engine
100% coverage")]
A -->|prompt| B
B -->|tool call| C
C -->|function call| D
D -->|"DayResult + ComplianceResult"| C
C -->|"JSON content block"| B
B -->|"plain-English answer with citations"| A
classDef user fill:#0b3d91,stroke:#fff,color:#fff
classDef host fill:#5b1ea3,stroke:#fff,color:#fff
classDef mcp fill:#1f6f43,stroke:#fff,color:#fff
classDef core fill:#7c4a03,stroke:#fff,color:#fff
class A user
class B host
class C mcp
class D coreTwo important properties:
Claude doesn't do the math. It picks a tool, fills the arguments, and forwards the answer. If the engine says "this was a late meal," the agent says "this was a late meal." If you re-ask the same question, you get the same answer — every time.
Time zones are explicit, not guessed. Every timestamp carries its own offset. The engine never reads the host clock, never assumes UTC, never silently converts. DST days work because you told it the offset, not because it inferred it.
Pick the MCP host you're already using. Same one-liner everywhere:
Edit ~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows:
{
"mcpServers": {
"attendance-engine": {
"command": "npx",
"args": ["-y", "@attendance-engine/mcp"]
}
}
}Fully quit and relaunch Claude Desktop (Cmd-Q on macOS — closing the window isn't enough).
~/.cursor/mcp.json:
{
"mcpServers": {
"attendance-engine": {
"command": "npx",
"args": ["-y", "@attendance-engine/mcp"]
}
}
}~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"attendance-engine": {
"command": "npx",
"args": ["-y", "@attendance-engine/mcp"]
}
}
}Launch the stdio binary directly:
npx -y @attendance-engine/mcpThe server speaks JSON-RPC over stdin/stdout — that's the whole contract.
🖼️ Scenario cards below are publish-ready SVG mockups (render inline on GitHub, npm, LinkedIn). Real-product screenshots can replace them when you capture them — see
docs/screenshots/README.md.
You: "Sara was on the 22:00→06:00 shift on June 1st. Punches: 21:54, 02:00, 02:30, 06:18. Apply California rules."
Claude (calls
evaluate_break_compliance): "Sara worked 7h54m on her duty date of June 1st (her clock-out fell on June 2nd but belongs to this shift). She took a 30-minute meal beginning at her 4-hour mark, which is compliant under California's mandate to start the first meal before the end of the 5th hour. Worked time spans midnight; flagged accordingly. She left 18 minutes past schedule — that 18m counts as overtime."
You: "Run an
audit_period_compliancefor employee EMP-007 across June 2026. Here are 30 days of punches and shifts. Use California."Claude: "3 days at high presumption risk — June 4, June 12, June 22. All three are late meals (started past the 5th hour). Total meal-period premium hours owed: 3. June 22 also drops below the 12-hour second-meal threshold. No rest-period violations detected."
You: "I have punches 09:00, 13:00, 14:00 for June 1st. Can I trust these?"
Claude (calls
diagnose_punches): "Recommendation: reject. The punch count is odd — one in or out is missing. Without that, worked-time and overtime would be guesses. Also: every punch falls on a 5-minute boundary, which often indicates manual entry rather than a device read. Worth verifying with the source system before resolving."
You: "Build me a 4-on-4-off roster for July 2026."
Claude (calls
generate_roster): "31 days — work days on July 1–4, 9–12, 17–20, 25–28 (12h day shifts, 07:00–19:00). Rest days fill the gaps. Want me to assign team rotations across this pattern?"
Tool | When you'd use it |
| "What happened on this single day? Lateness, OT, segments, flags." |
| "Roll up a week or a month: per-day results plus an aggregated summary." |
| "Did this person get their meal/rest breaks under California law? Is any premium owed?" |
| "Audit a whole pay period. Show me total premium hours, high-risk days, and the flag heatmap." |
| "Round worked/OT minutes to a unit — and keep the exact view alongside it so I can prove neutrality." |
| "Triage this raw punch stream. Should I trust it?" |
| "Build a 2-2-3 / 4-on-4-off / DuPont / Pitman / custom rotation." |
| "What jurisdictions are supported?" (currently CA; more arrive in minor releases) |
Resources you can paste into a chat:
URI | What it is |
| One-pager about the engine, time-zone rules, and how the tools compose. |
| Compact field-by-field API reference. |
| The California rule pack as JSON — meal/rest thresholds, waiver limits, premium caps, the citation source. |
Guided prompts (the host's / menu, or prompts/get):
analyse_timecard — walks the model through the right tool calls to analyse a single duty day.
roster_planner — generates a roster and renders it as a Markdown table.
Every ISO timestamp must carry its own offset:
✅ 2026-06-01T08:57:00+06:00
✅ 2026-06-01T08:57:00Z
❌ 2026-06-01T08:57:00 (rejected — the engine won't guess)
The engine reduces everything to absolute instants on a single timeline. DST works because the offsets are explicit. The duty date and shift HH:MM are worksite local wall-clock — match them to your business calendar, not to UTC.
For days with no punches (an absence, a holiday), pass policy.tzOffsetMinutes explicitly so the engine has something to anchor the shift window to.
Building your own host? Skip the CLI:
import { createServer } from '@attendance-engine/mcp';
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
const server = createServer({ name: 'my-hr-server', version: '1.0.0' });
await server.connect(new StdioServerTransport());Use it for: custom HTTP/SSE adapters, Claude Agent SDK setups, test harnesses, in-house deployments where the binary needs to live inside a bigger Node process.
Internal HR / payroll / workforce-analytics chat assistants
Audit-prep workflows for California employers
Customer-support tools at HR-tech vendors who need their AI to actually be right
Pre-payroll compliance triage ("which days need a human to review?")
Schedule planners that need a real roster engine, not vibes
A leave-balance / accrual system (the engine deals in minutes, not entitlements).
A payroll-money calculator (it gives you the hour buckets — you multiply by the rate).
A biometric device protocol (pair it with whatever ingest layer you've got).
A UI. There's no dashboard in here; that's a separate concern.
Node | 18+ (CI runs 20 LTS) |
MCP SDK | 1.x |
Engine |
|
Hosts tested | Claude Desktop 1.x · Cursor · Windsurf · any stdio MCP client |
Built by Md. Arifur Rahman. Companion to @attendance-engine/core (TypeScript) and arifur9993/attendance-engine (PHP). Same author, same fixtures, same answers — in three places your stack can reach for.
MIT — see LICENSE.
Produce a rounded view of a resolved day's worked & overtime minutes without losing the exact-minute result. Useful for the California-style 'exact-minute is the baseline; rounding must be provably neutral' pattern — keep both views and compare across populations.
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | ||
| rounding | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should fully disclose behavior. It explains that the tool keeps both rounded and exact-minute views, which is helpful. But it does not mention side effects, state changes, authorization needs, or output format, leaving gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loads the primary purpose, and includes a concrete use case. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complex nested parameters and no output schema, the description is brief. It explains the core function but omits details about the output structure, how the rounding unit/mode apply, and how it integrates with sibling resolve tools. It is adequate for a domain expert but not fully self-contained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 2 top-level parameters with no descriptions in the schema (0% coverage). The description adds no parameter-specific information, so the agent must infer meaning solely from the property names and nested schema, which is insufficient for correct invocation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool produces a rounded view of worked and overtime minutes while preserving exact-minute results. It distinguishes itself from siblings like resolve_day by focusing on rounding, and it specifies a domain context (California-style rounding pattern).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a specific use case ('California-style... pattern') and implies when to use it (after resolution, for rounding). However, it does not explicitly state when not to use or compare with siblings like audit_period_compliance or resolve_period, leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run a wage-and-hour compliance audit across multiple days. For each day, resolves attendance and evaluates meal/rest compliance under the chosen jurisdiction rule pack. Returns per-day breakdown plus period totals: hours of premium owed (meal + rest), days at risk, days with rebuttable-presumption exposure, and a flag-count heatmap. Use this for monthly payroll review, pre-audit triage, or a manager dashboard.
| Name | Required | Description | Default |
|---|---|---|---|
| employeeId | No | Optional employee identifier. Echoed in the report for downstream routing. | |
| jurisdiction | Yes | Jurisdiction rule pack. Currently CA only; more arrive in subsequent minor versions. | |
| days | Yes | One ResolveDayInput per duty date in the audit window. Order is preserved. | |
| waivers | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full responsibility for behavioral disclosure. It explains the tool resolves attendance and evaluates compliance, lists output elements (premium hours, days at risk, etc.), and notes jurisdiction limitations. It does not explicitly state whether the tool is read-only or has side effects, but the output focus suggests a read operation. The description is transparent enough for effective use.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at four sentences, each serving a clear purpose. It starts with the main action, then details the process and output, and ends with use cases. No extraneous information, and the structure is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the tool (nested inputs, no output schema), the description adequately covers the output structure and key behaviors. It lists the types of results (per-day breakdown, period totals, premium hours, risk days, etc.). It does not address error handling or edge cases, but the level of detail is sufficient for an agent to understand what the tool returns.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 75%, so baseline is 3. The tool description adds little beyond the schema: it mentions jurisdiction rule packs and output structure, but does not elaborate on parameter meanings or constraints. The schema already provides detailed descriptions for most parameters, so the description does not significantly enhance semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description starts with a specific verb 'Run a wage-and-hour compliance audit across multiple days' and clearly identifies the resource. It distinguishes the tool from siblings like resolve_day (single day) and evaluate_break_compliance (focused on breaks) by emphasizing multi-day, comprehensive audit with jurisdiction rules and per-day plus period totals.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit use cases: 'Use this for monthly payroll review, pre-audit triage, or a manager dashboard.' This gives clear positive guidance on when to use it. It does not explicitly state when not to use it or mention alternatives, but the context from siblings is sufficient for an agent to infer.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Triage raw clock punches before trusting them: count, sort, dedup, surface duplicates / odd-punch counts / round-number bias, report longest and shortest gaps, and (when an expected shift is provided) flag punches that fall outside it. Returns a recommendation: 'usable', 'review', or 'reject'.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | Duty date for the punches, YYYY-MM-DD. | |
| punches | Yes | ||
| expectedShift | No | Optional shift definition. When provided, the report flags punches outside [start - 4h, end + 4h] as off-shift. | |
| dedupeSeconds | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the tool's analytical actions (count, sort, dedup, etc.) and the output recommendation. It does not mention destructive intent or side effects, which is appropriate for a read-only diagnostic. Slightly more detail on non-modification would be ideal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the main action and provides a comprehensive overview without unnecessary words. Every clause adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested object parameters and no output schema, the description adequately explains the tool's behavior and output (a recommendation). It covers the key analytical aspects but lacks detail on the exact format of the return value or handling of edge cases like missing data.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50%; the description adds context for expectedShift (flags outside shift) but does not explain dedupeSeconds or the overall usage of punches array beyond the schema. The description compensates partially but could be more explicit about how each parameter influences the analysis.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: triage raw clock punches by counting, sorting, deduping, and surfacing anomalies. It specifies precise actions (duplicates, odd-punch counts, bias, gaps) and outputs a recommendation. This distinctly differentiates it from sibling tools like apply_rounding or audit_period_compliance.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage before trusting punches, providing a clear context. However, it does not explicitly state when not to use this tool or offer alternatives among siblings. The context 'before trusting them' is helpful but lacks explicit exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Analyse meal & rest period compliance for a duty day under a jurisdiction rule pack. v0.1 ships the California pack (Labor Code §§ 226.7, 512; IWC wage orders). Returns per-meal/rest analysis, premium hours owed at the regular rate, waiver issues, and rebuttable-presumption risk per Donohue v. AMN.
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | Raw inputs for the day under review. | |
| jurisdiction | Yes | Bundled jurisdiction rule pack to apply. Currently CA only; more arrive in subsequent minor versions. | |
| waivers | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It describes what the tool returns and references legal codes, but does not state whether it modifies data, requires authentication, or has performance implications. The mention of specific case law (Donohue v. AMN) adds context, but overall transparency is moderate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, consisting of three sentences that front-load the main purpose and include version and legal references. Every sentence contributes essential information without unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested inputs, no output schema), the description provides a useful overview of returned items but lacks details on output structure or behavior with invalid inputs. It is adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 67%. The description does not explain parameters in detail, but the schema itself provides decent coverage for 'input' and 'jurisdiction'. The description adds value by noting 'waiver issues' in the output, implying the waivers parameter's role. However, it does not compensate fully for the undocumented 'waivers' parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool analyzes meal and rest period compliance for a duty day under a specific jurisdiction rule pack (California). It lists specific return items (per-meal/rest analysis, premium hours, waiver issues, presumption risk), distinguishing it from siblings like audit_period_compliance or resolve_day.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide explicit guidance on when to use this tool versus its siblings. It mentions that v0.1 only supports California, but lacks instructions on alternatives for other jurisdictions or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a rotating roster from a built-in pattern ('2-2-3', '4-on-4-off', 'dupont', 'pitman') or a custom day cycle. Returns one assignment per calendar date with shift label and HH:MM window, or null on rest days.
| Name | Required | Description | Default |
|---|---|---|---|
| pattern | Yes | ||
| startDate | Yes | ||
| days | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description fully carries burden. It discloses input constraints (pattern format, date format, day count) and output structure (shift label, time window, null for rest). Does not state side effects, but generation is likely read-only. Adequate for a generation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: first states purpose and options, second details output. No fluff, every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists; description covers return values completely (assignment per date with shift label and time window, null for rest). All parameters explained. Adequate for full understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% description coverage; description compensates by explaining the two options for 'pattern' (built-in enums listed, plus custom object with array of off or objects) and mentions 'startDate' and 'days' formats. Adds significant meaning beyond raw schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description explicitly states 'Generate a rotating roster' and details output format (assignment per date with shift label and time window, or null). Clearly distinguishes from siblings which are unrelated (e.g., rounding, compliance).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Describes inputs (built-in patterns or custom cycles) and output, but does not specify when to use or avoid, nor prerequisites. Given sibling tools are unrelated, context is adequate but lacks explicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List bundled jurisdiction rule packs (meal/rest compliance). Returns each pack with id, human label, citation source, and full rule definitions.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes output but does not disclose any behavioral traits beyond listing (no annotations provided). Since it's a simple parameterless list, it is adequate but could mention any restrictions or prerequisites.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence that efficiently conveys purpose, domain, and output details with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters and no output schema, the description provides sufficient context about what the tool does and returns. Could note the absence of filters, but the empty schema already implies that.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so schema coverage is 100%. Description adds value by detailing what is returned (id, label, citation, full rules), compensating for lack of output schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool lists bundled jurisdiction rule packs for meal/rest compliance, and describes the return fields (id, label, citation, rules). Distinct from siblings which deal with other compliance functions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implied that this is a read-only listing for rule packs, but no explicit when-to-use or when-not-to-use guidance, nor mention of alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Resolve a single duty day from raw clock punches and a shift definition. Returns a structured DayResult with status, worked minutes, lateness, early-out, overtime, overnight handling, breaks-deducted minutes, data-integrity flags, and the resolved in/out segments.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | Duty date in worksite local wall-clock, YYYY-MM-DD. | |
| punches | Yes | ||
| shift | Yes | ||
| policy | No | ||
| leave | No | ||
| holiday | No | ||
| weekend | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but the description details what the tool returns (status, minutes, flags, segments), giving good insight into its behavior. However, it doesn't mention side effects or statelessness.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence that efficiently conveys purpose and outputs, though it could be broken into two for readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and no annotations; the description gives a good overview but lacks depth on input parameters, making it moderately complete for a complex tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 14%, but the description provides no additional meaning for the 7 parameters beyond mentioning 'raw clock punches and a shift definition.' It fails to explain policy, leave, etc.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool resolves a single duty day from punches and a shift definition, listing specific outputs. It distinguishes from sibling like resolve_period (period vs day).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool over siblings (e.g., resolve_period, diagnose_punches) or when not to use it. The description only states what it does.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Resolve a sequence of duty days (a week, a pay period, a month). Returns per-day DayResult entries; optionally include an aggregated PeriodSummary with attendance rate and flag counts.
| Name | Required | Description | Default |
|---|---|---|---|
| days | Yes | Inputs for each duty day in the period. | |
| summary | No | Include the aggregated PeriodSummary. Default: true. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the tool returns per-day DayResult entries and optionally a PeriodSummary with attendance rate and flag counts, which gives basic behavioral insight. However, no annotations exist, so the description carries the full burden, and it does not mention side effects, authentication requirements, or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose and output structure. Every sentence adds essential information. No redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the tool (nested input schema for days) and absence of output schema, the description adequately covers purpose and output but lacks context on return value details, edge cases, or practical constraints. It is minimally complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Parameter descriptions in the schema already cover 100% of parameters. The description adds minimal value beyond the schema, only reiterating the optional nature of the summary parameter. Therefore, rating is baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool resolves a sequence of duty days, specifying possible timeframes (week, pay period, month) and output structure (per-day entries, optional aggregated summary). This specificity distinguishes it from siblings like resolve_day and audit_period_compliance.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for a period of multiple days versus resolve_day for a single day, but it lacks explicit guidance on when to use this tool versus alternatives or any prerequisites. No 'when not to use' information is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0apply_roundingaudit_period_compliancediagnose_punchesevaluate_break_compliancegenerate_rosterlist_rule_packsresolve_dayresolve_periodScored across 8 tools
Each tool targets a distinct operation (rounding, auditing, diagnosing, evaluating, generating, listing, resolving single day, resolving period) with clear and non-overlapping purposes. Even similar tools like audit_period_compliance and evaluate_break_compliance are differentiated by scope (period vs single day, comprehensive audit vs specific break analysis).
All tool names follow a consistent verb_noun pattern in snake_case (e.g., apply_rounding, diagnose_punches, list_rule_packs). There is no mixing of conventions or vague verbs.
The 8 tools cover the core workflows of an attendance engine (punch triage, day/period resolution, compliance, rounding, roster generation, rule pack listing) without being excessive. The count is well-scoped for the domain.
The tool surface covers most essential operations: raw punch diagnosis, day/period resolution, compliance audits, rounding, roster generation, and rule pack listing. Minor gaps exist, such as the lack of a tool to apply rounding to a period or to modify rule packs, but the set is functional for typical use cases.
MCP server exposing klokin time-tracking operations (employees, time entries, stores) to AI clients.
MCP server providing attendance data queries via the CloudTime API.
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
Hosted MCP server for Cliniko — patients, appointments, availability, and invoices for AI agents.
