Skip to main content
Glama
Sign In

XBOSS

by kr.xdata
OverviewDiscussionsAdmin

건강보험·국민연금 보험료 요약

payroll_pack__premium_summary_v1__generate
Read-only

Composite premium summary v1: searches NHIS and NPS premium notices, then passes each selected row to the corresponding premium-summary step. The amounts are institution-notice totals billed to the workplace, including BOTH employee and employer portions; they are NOT the employee payroll-deduction amounts, so compute the employee share separately. Requires prior session login for 건강보험·국민연금. One 고지 (고지년월 + 고지차수) reissued as several NHIS 작성회차 (WRT_CHASU) resolves to the newest revision. When no row key or filter narrows the search to one 고지, each summary uses the newest 고지 of its provider (latest 고지년월, then latest round within it); a tie, or a row whose age cannot be read, stays skipped unless the provider-specific row key disambiguates it. No account_link_id is needed here: each step finds its own institution link. If computed is null the result could not be assembled: read computed_error for the reason and do not present the result as complete. Two shapes carry that case: this envelope with partial set to true (we fetched everything - the legs hold it - but could not calculate), or an error whose data carries the same envelope. partial is true whenever the result is incomplete, whether a leg failed or the calculation did. Files: a document generated from this result, as Excel (xlsx) only when requested in output_formats, listed in artifacts[] of the result with a download_url that works for 15 minutes; each file is kept for 7 days. If a link has expired, call xdata__job__result with the pack_run_id from the result for fresh links. For an anonymous result, keep its private recovery_receipt and send it with the original job_id or pack_run_id to xdata__job__result. It grants access to that result only, until the original file retention expires. Do not publish it. Losing it cannot be repaired by signing up. The receipt also works if the client later signs in; it does not grant access to other results. Without a receipt, results require the original account and lane. 호출마다 토큰 1소진

Input Schema

NameRequiredDescriptionDefault
goji_roundNoOptional NHIS notice round
nps_row_keyNoOptional NPS row key from pension notice search. Without it the newest notice is used; pass it to summarize an older notice or to settle a tie between equally new notices
nhis_row_keyNoOptional NHIS row key from premium notice search. Without it the newest notice is used; pass it to summarize an older notice or to settle a tie between equally new notices
output_formatsNoOptional. Also return this result as a file (Excel (xlsx)) in artifacts[] of the result. Omit it for data only.
idempotency_keyNoOptional outer idempotency key; leg keys are derived deterministically from this value.
nhis_document_idNoNHIS summary document: BMBB_030=regular, BMBB_050=adjustedBMBB_030
installment_roundNoNPS installment round: 1=ED02, 2=ED08. Optional; omit to use the most recent notice.
notice_year_monthNoTarget notice year-month in YYYYMM format. Optional; omit to use the most recent notice.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / installment_round / description
      Previous value: -"NPS installment round: 1=ED02, 2=ED08"New value: +"NPS installment round: 1=ED02, 2=ED08. Optional; omit to use the most recent notice."
    • changedInput schema / properties / nhis_row_key / description
      Previous value: -"Optional NHIS row key from premium notice search, used only to disambiguate multiple exact matches"New value: +"Optional NHIS row key from premium notice search. Without it the newest notice is used; pass it to summarize an older notice or to settle a tie between equally new notices"
    • changedInput schema / properties / notice_year_month / description
      Previous value: -"Target notice year-month in YYYYMM format"New value: +"Target notice year-month in YYYYMM format. Optional; omit to use the most recent notice."
    • changedInput schema / properties / nps_row_key / description
      Previous value: -"Optional NPS row key from pension notice search, used only to disambiguate multiple exact matches"New value: +"Optional NPS row key from pension notice search. Without it the newest notice is used; pass it to summarize an older notice or to settle a tie between equally new notices"
    • removedInput schema / required
      Removed value: -[
-  "notice_year_month",
-  "installment_round"
-]
  2. Changed1 schema field changed
    • addedInput schema / properties / output_formats
      Added value: +{
+  "description": "Optional. Also return this result as a file (Excel (xlsx)) in artifacts[] of the result. Omit it for data only.",
+  "items": {
+    "enum": [
+      "xlsx"
+    ],
+    "type": "string"
+  },
+  "minItems": 1,
+  "type": "array",
+  "uniqueItems": true
+}
  3. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Despite readOnlyHint=true covering the safety profile, the description adds substantial context beyond annotations: that amounts are institution-notice totals including employee AND employer portions (not payroll deductions), one-token-per-call consumption, idempotency-key derivation, the partial/computed_error envelopes, artifact retention (7 days) and 15-minute download links, and the private recovery_receipt handling. These are genuinely useful behavioral disclosures an agent could not infer from 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.

Conciseness3/5

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

The purpose and amount caveat are front-loaded well, but the description is a dense multi-topic wall mixing semantics, envelopes, file retention, receipts, and token cost. Much earns its place, yet the packing and some redundancy (receipt behavior restated several ways) reduce readability rather than crisp conciseness.

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?

There is no output schema, so the description carries the return-value burden, and it does: envelopes, partial flag, computed_error, artifacts[]/download_url, and recovery via xdata__job__result. For a complex composite tool with 8 params, nothing an agent needs to call or interpret results correctly is missing.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning about how parameters interact: row keys disambiguate older notices and settle ties, and absent a narrowing key the newest 고지 per provider is used with a defined tie/skip rule. This selection logic is not fully expressed in the schema and compensates usefully.

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 opening sentence gives a specific verb (composite summary/generate) plus the two resources it spans (NHIS and NPS premium notices) and describes the mechanism (search then pass each selected row to the corresponding premium-summary step). This clearly distinguishes it from the single-institution summary siblings and an agent can tell what it produces without opening the 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?

It states prerequisites (prior session login for 건강보험·국민연금), clarifies no account_link_id is needed, and explains when to pass row keys vs omit them to get the newest 고지, including tie behavior. What it lacks is explicit routing against sibling tools (e.g., when to call the underlying per-institution summary instead), so it is clear context but not full when/when-not guidance.

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

All XBOSS toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources