Skip to main content
Glama

日本の給与・社会保険・労働法

by io.github.kishida-devil

給与計算をまとめて — 事業所全員分と合計

calculate_payroll_batch

Runs calculate_payslip for many employees in one call and returns the run totals: gross, employee deductions, net, and employer cost.

Reach for this the moment more than two or three people are in play. A monthly payroll is not a sequence of unrelated questions — the employer share, the totals and the run id only mean anything across the whole run. Asking one employee at a time gives no total and no way to tell a retry from a second run.

Put anything shared in defaults (prefecture, business_type, column) and let each row carry only what differs, which is usually pay and age. A row that cannot be computed comes back in errors with its index and id while the rest of the run completes — do not discard a whole payroll over one bad row.

The reply carries a run_id derived from the route and the exact input, so sending the same payroll twice gives the same id. Nothing is stored, so a retry cannot double-count.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
compactNoDrop the per-employee breakdown and keep the payout figures — about a tenth the size on a large run. Use it when the question is "what do we pay", not "why".
defaultsNoApplied to any row that leaves the field out.
employeesYesOne entry per employee. Up to 500 on a paid plan, 10 on the free tier.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly reveals deterministic run_id derivation, that nothing is stored so retries cannot duplicate a run, and that partial failures return errors with index and id while the rest of the run completes. These are non-obvious behaviors essential for safe invocation.

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

Conciseness5/5

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

The description is front-loaded with the core purpose in the first sentence. Each subsequent paragraph earns its place: usage triggers, parameter strategy, error semantics, and idempotency. It is detailed but not bloated, with no redundant sentences.

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

Completeness5/5

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

For a complex batch tool with no output schema and no annotations, the description covers the essential operational context: what the return totals are, how run_id behaves across retries, how partial errors are handled, and how to organize the input. Nothing an agent needs to call this correctly is left unclear.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds meaningful guidance beyond the schema by advising users to put shared values in defaults (prefecture, business_type, column) and only differing values per row, and by explaining how errors reference row index and id. This elevates the guidance without needing to restate every field.

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?

The description opens with a specific verb and resource: 'Runs calculate_payslip for many employees in one call and returns the run totals.' It further clarifies the unique value (gross, employee deductions, net, employer cost) and differentiates itself from the single-employee sibling tool calculate_payslip.

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

Usage Guidelines5/5

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

The description explicitly states when to use the tool: 'Reach for this the moment more than two or three people are in play.' It also explains why the alternative (asking one employee at a time) is inadequate, and provides guidance on structuring inputs via defaults, making the decision context complete.

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

All 日本の給与・社会保険・労働法 toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation4/5

Most tools have distinct, well-defined jobs—payroll calculations, revision judgments, eligibility checks, and data lookups are clearly separated. The main remaining risk is among the standard-remuneration judgment tools and the batch/singleton pairs, but their descriptions are detailed enough to prevent serious misselection.

Naming Consistency3/5

There is a reasonably recognizable pattern with calculate_, judge_, check_, get_, and validate_ groups. However, several noun-phrase names (business_days, consumption_tax, national_insurance, commuting_allowance_exemption) and overlapping verb choices (decide_ vs judge_ vs check_) prevent a fully consistent verb_noun convention.

Tool Count2/5

At 30 tools, the surface is materially larger than the 3–15 range that keeps an agent's selection burden low. Batch variants and three separate standard-remuneration revision tools add complexity, and although the domain is broad, the count feels heavy for an assistant to choose from confidently.

Completeness4/5

The core workflows are well covered: monthly pay, bonuses, overtime, standard-remuneration determination, year-end adjustment, resident tax, leave, worker classification, and invoice validation. Gaps exist around statutory benefit payments such as sickness or maternity allowances and retirement-specific processing, but most payroll and social insurance tasks can be completed without dead ends.

Resources