Skip to main content
Glama
Sign In
freee-mcp

freee-mcp

by newbdez33
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Preview a freee application action

freee_approval_prepare_action
Read-onlyIdempotent

Preview an approve, return, or cancel-approval action for a freee application, review work-time corrections, and get a binding fingerprint without changing the application.

Instructions

Read and preview one available approve, return, or cancel_approval action, including any structured 勤務時間修正 before/after comparison, and return a binding fingerprint. For an exact instruction or active scoped business policy, the Agent evaluates the complete detail and matches the fingerprint without per-item user confirmation. Before approving a 休暇 application, every pending approval-list page is checked for same-applicant, same-date 勤務時間修正 applications; a blocker or an unreliable applicant/date stops this item without a fingerprint. No application is changed.

Input Schema

NameRequiredDescriptionDefault
idYesThe numeric No. shown in the freee application list.
actionYesapprove maps to 承認; return maps to 申請者へ差し戻す; cancel_approval maps to 承認を取り消す on an approved application and must verify 差戻し. Canceling approval requires a precise instruction for this application; an approve/return policy does not authorize it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.6.0
    • changedInput schema / properties / action / description
      Previous value: -"approve maps to 承認; return maps to 申請者へ差し戻す."New value: +"approve maps to 承認; return maps to 申請者へ差し戻す; cancel_approval maps to 承認を取り消す on an approved application and must verify 差戻し. Canceling approval requires a precise instruction for this application; an approve/return policy does not authorize it."
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "approve",
-  "return"
-]New value: +[
+  "approve",
+  "return",
+  "cancel_approval"
+]
  2. First observedv0.3.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, so safety is partly covered; the description adds substantial behavior beyond that — a binding fingerprint, a cross-page scan of pending approval lists for same-applicant, same-date 勤務時間修正 before approving 休暇, and the rule that a blocker or unreliable applicant/date aborts without a fingerprint. 'No application is changed' largely restates readOnlyHint rather than adding to it.

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?

Front-loaded with the core action and fingerprint outcome, then prerequisites, then the no-mutation guarantee. The middle sentences are dense and clause-heavy with mixed Japanese/English terminology, but nearly every clause carries operational information rather than filler.

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

Completeness4/5

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

With no output schema, the description usefully discloses what comes back (a binding fingerprint plus any structured 勤務時間修正 before/after comparison) and what failure looks like (no fingerprint). What is missing is the handoff — what to do with the fingerprint, i.e. pass it to the commit tool — which is the most important remaining gap for a two-parameter prepare/commit pair.

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

Parameters3/5

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

Schema coverage is 100% and the enum description already maps approve/return/cancel_approval to the Japanese UI labels and states the precise-instruction requirement for cancel_approval. The description adds little parameter-level meaning beyond that, so the baseline 3 applies; the 勤務時間修正 before/after detail concerns output, not input.

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?

States a specific verb+resource: read and preview one available approve, return, or cancel_approval action, returning a binding fingerprint. The preview-versus-apply distinction is clear from 'No application is changed', which implicitly separates it from the commit sibling, though freee_approval_commit_action is never named.

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?

Gives concrete when-to-use context: for an exact instruction or an active scoped business policy, the Agent may match the fingerprint without per-item user confirmation, and the description explains when the item is stopped. It does not explicitly state that this must be called before the corresponding commit tool, leaving the two-phase workflow to inference.

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

Deploy Server

Other Tools