Skip to main content
Glama

Taokeh MCP server

File a pending recurring-invoice change draft (human approves in Taokeh)

update_recurring_invoice_draft

FILES A PENDING DRAFT ONLY — NOTHING CHANGES UNTIL A HUMAN REVIEWS AND APPROVES IT IN TAOKEH. Propose changes to a recurring invoice ALREADY set up in Taokeh — a price rise across a subscription, a changed quantity, a new end date, a cadence correction, or PAUSING the billing. This does NOT change anything: it files a pending DRAFT the owner reviews as a DIFF (current → proposed, changed fields only) and approves; only that tap writes. Name the schedule with recurringId, its real id — there is NO name fallback, because a schedule title is free text and one customer often has two schedules (a monthly retainer and an annual licence), so guessing between them would re-bill the wrong contract. proposed holds ONLY what you want changed: title, customerId/customer, lines, cadence, paymentMethod, startDate, endDate, maxOccurrences, notes, and status ("paused" to stop future invoices, "active" to resume). ⚠ lines is WHOLE-REPLACE: send every line the schedule should have, including the unchanged ones — for a price rise, send the same lines with the new prices. ⚠ APPROVING CAN MOVE THE BILLING DATE even when you change only a price: Taokeh re-derives the next issue date from the start date on every save, so the review page states the exact date the next invoice would go out, and whether that has moved. ⛔ WHAT IT CANNOT DO, each refused by name: it cannot set issueMode: "auto" — that would let one approval remove the human tap from every future invoice; it cannot set status: "ended", a ONE-WAY door no later draft could undo (propose "paused" instead, which stops the billing just as completely and can be resumed); it cannot set MFRS 15 revenue spreading, an accounting-policy decision on the schedule's own page; and it cannot touch the invoices this schedule has ALREADY issued — a change reaches the next firing and no earlier one. If a past invoice was wrong, credit it (create_credit_note_draft); the schedule only decides what happens next. A field the record already agrees with is dropped, and a proposal that changes nothing is refused rather than filed as an empty diff. One schedule per call — loop for a sweep across several, because each reviewable diff is the point.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
notesNoA SHORT reviewer note, in the reviewer's language: what you changed, why, and what they should double-check.
proposedYesONLY the fields you want changed. A field the record already agrees with is dropped; an unknown or deliberately-excluded field is refused by name.
needsReviewNoSet true when something gave you pause — a price the user was unsure about, a date you inferred.
recurringIdYesThe recurring invoice's real id. Required — there is no name fallback.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / proposed / properties / lines / description
      Previous value: -"WHOLE-REPLACE. Send every line the schedule should bill from now on, not just the changed ones — a partial set would silently drop the rest."New value: +"WHOLE-REPLACE. Send every line the schedule should bill from now on, not just the changed ones — a partial set would silently drop the rest. ⛔ LINE KEYS ARE STRICT, exactly as on create_recurring_invoice_draft: a key this schema does not list is REFUSED BY NAME and NOTHING is filed."
    • addedInput schema / properties / proposed / properties / lines / items / additionalProperties
      Added value: +false
    • addedInput schema / properties / proposed / properties / lines / items / properties / description / description
      Added value: +"The line text as PRINTED on the document, when it says more than the product name does — a size, a grade, a job reference, a period covered. It rides onto the posted line and prints on the customer's copy, so send what the paper says rather than a tidier phrasing of your own. Leave it out when the product name already says it. This is TEXT, not a field: Taokeh has no column for a dimension, a grade or a variant, so anything of that kind belongs here."
    • addedInput schema / properties / proposed / properties / lines / minItems
      Added value: +1
  2. Added

TDQS

A4.9/5.0
Behavior5/5

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

Annotations are sparse (all false), so the description carries the full burden, and it delivers richly. It discloses the draft/approval two-step, the whole-replace semantics of lines, the fact that approving can move the billing date even on a price-only change, the one-way door of 'ended', the refusal of no-op proposals, and the dropping of unchanged fields. It also warns about the absence of a name fallback and why. This goes well beyond what annotations could convey.

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?

The description is long but every section earns its place: the opening warning, the use cases, the parameter semantics, the explicit refusals, and the operational notes. It is front-loaded with the most critical fact (nothing changes until human approval) and uses typographic signals (⚠, ⛔, ALL-CAPS) to structure scanning. It loses one point for length and some redundancy (e.g., the 'paused' explanation appears twice), but it remains well-organized and readable.

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 tool with nested objects, 4 parameters, no output schema, and sparse annotations, the description is remarkably complete. It covers what the tool does, what it cannot do, how parameters behave, what the human review entails, and how to handle multi-schedule sweeps. The only minor gap is the lack of an explicit return value description, but since there is no output schema and the tool's purpose is to file a draft, the absence is not material. An agent has everything needed to invoke it correctly.

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

Parameters5/5

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 substantial meaning beyond the schema. It explains the real-world consequence of endDate null (extends billing indefinitely), the reviewer-facing meaning of notes, the strict line keys, the whole-replace semantics, and the status enum's behavioral implications (paused is reversible, ended is refused). It also clarifies the customer/customerId alternative and the no-name-fallback rule for recurringId. This is high-value semantic enrichment, not repetition.

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 loud, specific statement: 'FILES A PENDING DRAFT ONLY — NOTHING CHANGES UNTIL A HUMAN REVIEWS AND APPROVES IT IN TAOKEH.' It names the exact verb (file/propose), the resource (recurring invoice already set up in Taokeh), and the scope (pending draft for human approval). It distinguishes itself from create_recurring_invoice_draft and update_invoice_draft by emphasizing it only proposes changes to an existing schedule, and it lists concrete use cases (price rise, quantity, end date, cadence, pausing). This is far beyond a vague purpose statement.

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 gives explicit when-to-use guidance: use it to propose changes to an already-set-up recurring invoice, and explicitly says what it cannot do (set issueMode auto, set status ended, set MFRS 15, touch already-issued invoices). It also names the alternative for past invoice corrections: 'If a past invoice was wrong, credit it (create_credit_note_draft); the schedule only decides what happens next.' It even gives a looping instruction for sweeping multiple schedules. This is textbook usage guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources