Skip to main content
Glama

List missing invoices

well_list_missing_invoices
Read-only

List the supplier invoices a past period is still missing — the settled spend whose invoice has not been collected, one row per counterparty, exactly as the Well app's expense-invoices card shows them. Use it for "which invoices am I missing for ?" and as the input to fetching them.

Name the period ONE way: { calendar_year, calendar_month } (the calendar month, e.g. June 2026 → 2026, 6), { fiscal_year, fiscal_period }, or periods: [{ calendar_year, calendar_month }, …] for SEVERAL months in one call (1-12), or name NO period at all to use the months the user selected on the period card in this conversation (well_list_periods → the user clicks → well_switch_workspace records them). With no period named and no months selected, the call refuses and tells you to run the period step first. Every month must have ended: a current or future month is refused, and so is the adjustment period (13). Duplicate months are refused.

COST: there is no batch endpoint, so each named month is a separate read of that month's spend. Ask for the months the user actually named, not a whole year "to be safe".

Returns rows, ONE per counterparty for the whole call, never one per month. Each row carries name, tx_count and base_total_amount in base_currency SUMMED over the months it covers, its own months array naming those months (each with that month's tx_count, base_total_amount, proof_task_id, acquisition_status and refusal_reason), and the route fields mode, available_modes, suggested_action, matched_provider_name and matched_connector_service_id, which the provider match resolves once per counterparty. NEVER list a counterparty once per month and never present its months as separate gaps: it is one supplier to chase, and one collection covers every month behind it. Name the months a row spans from its months array. The envelope's own months carries each month's totals (rows are NOT repeated there), periods_covered names the months read, and transaction_count, group_count and dropped_groups are totals across every month read. row_count counts the DISTINCT counterparties, so it is never the sum of the months' own row_count. dropped_groups counts the GROUPS that produced no row — party-less bank operations, unresolved counterparties, unnamed companies — never transactions, and bank_internal and unknown hold one group per month whatever they contain, so quote neither as a quantity of operations. unknown and unnamed_company ARE categorized expense spend still missing a supplier invoice, so an empty rows over a non-zero count is not a complete period; bank_internal alone is, since no supplier can invoice a party-less operation. The single-month fields calendar_year, calendar_month, fiscal_year, fiscal_period and period_label appear ONLY when the call named exactly one month.

Every row also carries transactions — the counterparty's own lines behind the row, each with date, description (the bank's remittance text), category, amount, currency and base_amount. amount is signed and stays in the transaction's own currency, so never add those together across a row; base_amount is the same line in base_currency, and the magnitudes of those DO add up to base_total_amount. The list is capped at 25 per row and transactions_omitted says how many the cap left out — quote that number instead of implying the list is complete.

mode is the ONE route the card suggests for that row: agent (a browser agent can collect it from the supplier portal), connect (connect the named service and Well fetches it), upload (the user supplies the file). available_modes lists every route the row offers instead of only the suggested one — agent and upload on every row, plus connect when the catalog holds a connector for the matched provider, so 2 or 3 entries. Present mode as the suggestion and available_modes as the choice.

Only CATEGORIZED expense transactions are considered — uncategorized spend is not listed, so poor categorization coverage under-reports the gaps; disclose the hints.

This tool reads the user's data and changes none of it. It does not mint tasks, start a close, connect anything, or fetch any invoice.

Call this directly — no other tool call is needed first (workspace is resolved from the caller's authorized token, same as every other well_* tool).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
periodsNoSeveral calendar months in one call, 1-12. Each month costs one separate read, so name only the months you need. Duplicates are refused.
fiscal_yearNoFiscal year (the calendar year the workspace's fiscal year STARTED in).
workspace_idNoTarget workspace. This read reports one workspace's own data. Omit it and the token's primary workspace answers, which may not be the one you mean; the result names the workspace that did.
calendar_yearNoCalendar year, e.g. 2026.
fiscal_periodNoFiscal period, 1-12. The adjustment period (13) is refused: it has no calendar month.
calendar_monthNoCalendar month, 1 = January … 12 = December.
conversation_idNoThe conversation id returned by the previous Well result, in its meta under well/conversation_id, in its structuredContent, or in its JSON text block. Pass it back on every call in the same conversation, including a call a card makes, so the chosen workspace and the earlier answers still apply. It decides the conversation on its own: nothing the host states about the session replaces it. Omit it only on the first call of a conversation.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
rowsYesThe card's rows, ONE per counterparty for the whole call, in the order the oldest month listed them, each naming the months it covers in `months`. A counterparty owing an invoice in several of the months read is one row, never one per month.
errorNo
hintsNo
monthsNoPer-month totals, oldest first.
successYes
next_stepNoWhat to do with the card this result renders. Added by the dispatcher when the card asks for a click.
row_countNoRows in `rows`, which is the DISTINCT counterparties the call found. Never the sum of the months' own `row_count`.
fiscal_yearNoPresent only when the call named exactly one month.
group_countNoGroups the reads returned before the card's projection.
period_labelNoHuman-readable label of the period, e.g. "June 2026". Present only when the call named one month.
workspace_idNo
base_currencyNo
calendar_yearNoPresent only when the call named exactly one month.
fiscal_periodNoPresent only when the call named exactly one month.
calendar_monthNoPresent only when the call named exactly one month.
dropped_groupsNo
conversation_idNoThe conversation this result belongs to. Pass it back as the conversation_id argument on every later Well call in the same conversation.
periods_coveredNoThe months the result covers, oldest first.
periods_requestedNoHow many calendar months the call named.
transaction_countNoEvery transaction missing its invoice, across all groups and all months.
resolved_workspaceNoThe workspace that answered, when the caller named none and the token authorizes several.
conversation_id_noteNoPresent only when the server opened a fresh lane, stating that no choice recorded earlier was read.
conversation_id_sourceNoWhere the conversation id came from: the host's own request meta, the caller's argument, or a fresh lane the server opened.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / conversation_id
      Added value: +{
      +  "description": "The conversation id returned by the previous Well result, in its meta under well/conversation_id, in its structuredContent, or in its JSON text block. Pass it back on every call in the same conversation, including a call a card makes, so the chosen workspace and the earlier answers still apply. It decides the conversation on its own: nothing the host states about the session replaces it. Omit it only on the first call of a conversation.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / conversation_id
      Added value: +{
      +  "description": "The conversation this result belongs to. Pass it back as the conversation_id argument on every later Well call in the same conversation.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / conversation_id_note
      Added value: +{
      +  "description": "Present only when the server opened a fresh lane, stating that no choice recorded earlier was read.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / conversation_id_source
      Added value: +{
      +  "description": "Where the conversation id came from: the host's own request meta, the caller's argument, or a fresh lane the server opened.",
      +  "enum": [
      +    "host_meta",
      +    "argument",
      +    "minted"
      +  ],
      +  "type": "string"
      +}
  2. Changed2 schema fields changed
    • changedOutput schema / properties / rows / items / properties / mode / description
      Previous value: -"How the app's card offers to obtain the invoice: agent (a browser agent runs the supplier portal — a published blueprint exists), connect (connect matched_connector_service_id and Well fetches it), upload (the user supplies the file). Already downgraded from suggested_action when the automated route cannot be honoured."New value: +"How the app's card offers to obtain the invoice: agent (a browser agent runs the supplier portal — the provider carries a blueprint OR a real portal URL the agent runs against), connect (connect matched_connector_service_id and Well fetches it), upload (the user supplies the file). Decided from the provider facts: connect wins when a connector matched, else agent when it can run, else upload."
    • changedOutput schema / properties / rows / items / properties / suggested_action / description
      Previous value: -"The backend's raw routing decision, before the downgrade rules."New value: +"The backend's routing decision for the row. `chrome_extension_fetch` when the matched provider can run the browser agent (a blueprint or a real portal URL), `connect_provider` when a connector matched, else `manual_upload`. `mode` is the same decision in the card's vocabulary."
  3. Changed1 schema field changed
    • addedOutput schema / properties / next_step
      Added value: +{
      +  "description": "What to do with the card this result renders. Added by the dispatcher when the card asks for a click.",
      +  "type": "string"
      +}
  4. Changed2 schema fields changed
    • addedOutput schema / properties / rows / items / properties / matched_provider_url
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ]
      +}
    • changedOutput schema / properties / rows / items / required
      Previous value: -[
      -  "id",
      -  "company_id",
      -  "name",
      -  "logo_url",
      -  "domain_resolution",
      -  "months",
      -  "tx_count",
      -  "transactions",
      -  "transactions_omitted",
      -  "base_total_amount",
      -  "mode",
      -  "available_modes",
      -  "suggested_action",
      -  "matched_provider_name",
      -  "matched_provider_has_blueprint",
      -  "matched_connector_service_id"
      -]New value: +[
      +  "id",
      +  "company_id",
      +  "name",
      +  "logo_url",
      +  "domain_resolution",
      +  "months",
      +  "tx_count",
      +  "transactions",
      +  "transactions_omitted",
      +  "base_total_amount",
      +  "mode",
      +  "available_modes",
      +  "suggested_action",
      +  "matched_provider_name",
      +  "matched_provider_url",
      +  "matched_provider_has_blueprint",
      +  "matched_connector_service_id"
      +]
  5. Changed1 schema field changed
    • changedOutput schema / properties / rows / items / properties / logo_url / description
      Previous value: -"The counterparty's mark, resolved in that order: the matched provider's stored logo, else the counterparty company's own stored logo — the one company enrichment resolved from that company's domain — else the mark derived from the matched portal's host. Null when the row matched no portal and its company carries no logo, and the card then draws initials."New value: +"The counterparty's mark: the matched provider's stored logo, else the counterparty company's own stored logo — the one company enrichment resolved from that company's domain. Null when the row matched no provider and its company carries no stored logo. A null here does not mean the card draws initials: the widget is additionally offered a mark derived from the company's own host, which this field never carries."
  6. Changed2 schema fields changed
    • addedOutput schema / properties / rows / items / properties / domain_resolution
      Added value: +{
      +  "description": "The counterparty company's own domain-discovery state: 'resolved' when it already carries a domain (any source); 'pending' when a web-evidence resolve is durably enqueued and still open; 'none' when no domain is known and nothing is in flight.",
      +  "enum": [
      +    "resolved",
      +    "pending",
      +    "none"
      +  ],
      +  "type": "string"
      +}
    • changedOutput schema / properties / rows / items / required
      Previous value: -[
      -  "id",
      -  "company_id",
      -  "name",
      -  "logo_url",
      -  "months",
      -  "tx_count",
      -  "transactions",
      -  "transactions_omitted",
      -  "base_total_amount",
      -  "mode",
      -  "available_modes",
      -  "suggested_action",
      -  "matched_provider_name",
      -  "matched_provider_has_blueprint",
      -  "matched_connector_service_id"
      -]New value: +[
      +  "id",
      +  "company_id",
      +  "name",
      +  "logo_url",
      +  "domain_resolution",
      +  "months",
      +  "tx_count",
      +  "transactions",
      +  "transactions_omitted",
      +  "base_total_amount",
      +  "mode",
      +  "available_modes",
      +  "suggested_action",
      +  "matched_provider_name",
      +  "matched_provider_has_blueprint",
      +  "matched_connector_service_id"
      +]
  7. Changed15 schema fields changed
    • addedOutput schema / properties / months / items / properties / row_count / description
      Added value: +"Counterparties THIS month is missing an invoice from. A counterparty owing an invoice in several months counts in each of them, so these do not sum to the envelope's `row_count`, which counts each counterparty once."
    • addedOutput schema / properties / row_count / description
      Added value: +"Rows in `rows`, which is the DISTINCT counterparties the call found. Never the sum of the months' own `row_count`."
    • changedOutput schema / properties / rows / description
      Previous value: -"The card's rows — one per counterparty per month, oldest month first, each tagged with its month."New value: +"The card's rows, ONE per counterparty for the whole call, in the order the oldest month listed them, each naming the months it covers in `months`. A counterparty owing an invoice in several of the months read is one row, never one per month."
    • removedOutput schema / properties / rows / items / properties / acquisition_status
      Removed value: -{
      -  "enum": [
      -    "waiting",
      -    "processing",
      -    "mapped",
      -    "refused"
      -  ],
      -  "type": "string"
      -}
    • changedOutput schema / properties / rows / items / properties / base_total_amount / description
      Previous value: -"Sum in base_currency; null when an FX rate was missing for any transaction."New value: +"Sum in base_currency across every month in `months`; null when an FX rate was missing for any transaction of any of them."
    • removedOutput schema / properties / rows / items / properties / calendar_month
      Removed value: -{
      -  "maximum": 9007199254740991,
      -  "minimum": -9007199254740991,
      -  "type": "integer"
      -}
    • removedOutput schema / properties / rows / items / properties / calendar_year
      Removed value: -{
      -  "maximum": 9007199254740991,
      -  "minimum": -9007199254740991,
      -  "type": "integer"
      -}
    • changedOutput schema / properties / rows / items / properties / id / description
      Previous value: -"Stable row key: the proof task id when one exists, else the counterparty company id."New value: +"Stable row key: the counterparty company id, or the proof task id of a gap that resolved no company. One key per counterparty for the whole call, so it never repeats across the months the row covers."
    • addedOutput schema / properties / rows / items / properties / months
      Added value: +{
      +  "description": "The months of the call this counterparty is missing an invoice in, oldest first: one entry, or several when the same counterparty owes an invoice in more than one of them. The envelope's `periods_covered` names every month READ; this names the months THIS row covers.",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "acquisition_status": {
      +        "enum": [
      +          "waiting",
      +          "processing",
      +          "mapped",
      +          "refused"
      +        ],
      +        "type": "string"
      +      },
      +      "base_total_amount": {
      +        "anyOf": [
      +          {
      +            "type": "number"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "description": "This month's sum in `base_currency`; null when an FX rate was missing for any of its transactions."
      +      },
      +      "calendar_month": {
      +        "maximum": 9007199254740991,
      +        "minimum": -9007199254740991,
      +        "type": "integer"
      +      },
      +      "calendar_year": {
      +        "maximum": 9007199254740991,
      +        "minimum": -9007199254740991,
      +        "type": "integer"
      +      },
      +      "period_label": {
      +        "description": "The month this row belongs to, e.g. \"June 2026\".",
      +        "type": "string"
      +      },
      +      "proof_task_id": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "description": "The close-proof task bound to this month's gap; null until one is minted."
      +      },
      +      "refusal_reason": {
      +        "anyOf": [
      +          {
      +            "enum": [
      +              "noop_not_proof",
      +              "noop_no_gap_match",
      +              "noop_ambiguous_gaps",
      +              "noop_task_unavailable",
      +              "warn_bridge_error"
      +            ],
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "description": "Populated only when THIS month's acquisition_status is refused."
      +      },
      +      "tx_count": {
      +        "description": "Transactions this counterparty is missing an invoice for in THIS month alone.",
      +        "maximum": 9007199254740991,
      +        "minimum": -9007199254740991,
      +        "type": "integer"
      +      }
      +    },
      +    "required": [
      +      "calendar_year",
      +      "calendar_month",
      +      "period_label",
      +      "tx_count",
      +      "base_total_amount",
      +      "proof_task_id",
      +      "acquisition_status",
      +      "refusal_reason"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • removedOutput schema / properties / rows / items / properties / period_label
      Removed value: -{
      -  "description": "The month this row belongs to, e.g. \"June 2026\".",
      -  "type": "string"
      -}
    • removedOutput schema / properties / rows / items / properties / proof_task_id
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "type": "string"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "description": "The close-proof task bound to this gap; null until one is minted."
      -}
    • removedOutput schema / properties / rows / items / properties / refusal_reason
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "enum": [
      -        "noop_not_proof",
      -        "noop_no_gap_match",
      -        "noop_ambiguous_gaps",
      -        "noop_task_unavailable",
      -        "warn_bridge_error"
      -      ],
      -      "type": "string"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "description": "Populated only when acquisition_status is refused."
      -}
    • changedOutput schema / properties / rows / items / properties / transactions / description
      Previous value: -"The row's own transactions, in ledger order, at most 25 — the same bounded sample the app's card lists under the counterparty."New value: +"The row's own transactions, oldest month first, at most 25 for the WHOLE row: the same bounded sample the app's card lists under the counterparty. A row spanning months carries one sample across them, not one per month."
    • addedOutput schema / properties / rows / items / properties / tx_count / description
      Added value: +"Transactions missing an invoice, summed across every month in `months`."
    • changedOutput schema / properties / rows / items / required
      Previous value: -[
      -  "id",
      -  "company_id",
      -  "name",
      -  "logo_url",
      -  "calendar_year",
      -  "calendar_month",
      -  "period_label",
      -  "tx_count",
      -  "transactions",
      -  "transactions_omitted",
      -  "base_total_amount",
      -  "mode",
      -  "available_modes",
      -  "suggested_action",
      -  "matched_provider_name",
      -  "matched_provider_has_blueprint",
      -  "matched_connector_service_id",
      -  "proof_task_id",
      -  "acquisition_status",
      -  "refusal_reason"
      -]New value: +[
      +  "id",
      +  "company_id",
      +  "name",
      +  "logo_url",
      +  "months",
      +  "tx_count",
      +  "transactions",
      +  "transactions_omitted",
      +  "base_total_amount",
      +  "mode",
      +  "available_modes",
      +  "suggested_action",
      +  "matched_provider_name",
      +  "matched_provider_has_blueprint",
      +  "matched_connector_service_id"
      +]
  8. Changed2 schema fields changed
    • changedInput schema / properties / workspace_id / description
      Previous value: -"Target workspace. Omit to use the only authorized workspace, or (for read tools) to query all authorized workspaces grouped by workspace. Required for write tools when the token authorizes more than one workspace."New value: +"Target workspace. This read reports one workspace's own data. Omit it and the token's primary workspace answers, which may not be the one you mean; the result names the workspace that did."
    • addedOutput schema / properties / resolved_workspace
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "The workspace that answered, when the caller named none and the token authorizes several.",
      +  "properties": {
      +    "name": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "workspace_id": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "workspace_id",
      +    "name"
      +  ],
      +  "type": "object"
      +}
  9. Changed11 schema fields changed
    • changedOutput schema / properties / dropped_groups / properties / bank_internal / description
      Previous value: -"Party-less bank operations — nothing to collect."New value: +"GROUPS of party-less bank operations — nothing to collect. One group per month that held any, NOT a count of operations: never quote this number as a quantity of bank operations."
    • changedOutput schema / properties / dropped_groups / properties / unknown / description
      Previous value: -"Spend with no resolved counterparty."New value: +"GROUPS of spend with no resolved counterparty. One group per month that held any, NOT a count of transactions or of counterparties."
    • changedOutput schema / properties / dropped_groups / properties / unnamed_company / description
      Previous value: -"Counterparties the card cannot render (no name or no key)."New value: +"GROUPS the card cannot render (no name or no key) — one per company, NOT a count of transactions."
    • changedOutput schema / properties / months / items / properties / dropped_groups / properties / bank_internal / description
      Previous value: -"Party-less bank operations — nothing to collect."New value: +"GROUPS of party-less bank operations — nothing to collect. One group per month that held any, NOT a count of operations: never quote this number as a quantity of bank operations."
    • changedOutput schema / properties / months / items / properties / dropped_groups / properties / unknown / description
      Previous value: -"Spend with no resolved counterparty."New value: +"GROUPS of spend with no resolved counterparty. One group per month that held any, NOT a count of transactions or of counterparties."
    • changedOutput schema / properties / months / items / properties / dropped_groups / properties / unnamed_company / description
      Previous value: -"Counterparties the card cannot render (no name or no key)."New value: +"GROUPS the card cannot render (no name or no key) — one per company, NOT a count of transactions."
    • addedOutput schema / properties / rows / items / properties / available_modes
      Added value: +{
      +  "description": "Every collection method this counterparty offers, agent first and upload last — 2 or 3 entries, never one. `agent` and `upload` stand for every row; `connect` joins them only when the catalog holds a connector for the matched provider, which is exactly what a non-null matched_connector_service_id reports. `mode` names the ONE route the card suggests, this names all the routes the user may pick.",
      +  "items": {
      +    "enum": [
      +      "agent",
      +      "connect",
      +      "upload"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / properties / rows / items / properties / logo_url / description
      Previous value: -"The matched provider's logo; null when unmatched."New value: +"The counterparty's mark, resolved in that order: the matched provider's stored logo, else the counterparty company's own stored logo — the one company enrichment resolved from that company's domain — else the mark derived from the matched portal's host. Null when the row matched no portal and its company carries no logo, and the card then draws initials."
    • addedOutput schema / properties / rows / items / properties / transactions
      Added value: +{
      +  "description": "The row's own transactions, in ledger order, at most 25 — the same bounded sample the app's card lists under the counterparty.",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "amount": {
      +        "anyOf": [
      +          {
      +            "type": "number"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "description": "Signed amount in `currency` — negative when the money leaves the account."
      +      },
      +      "base_amount": {
      +        "anyOf": [
      +          {
      +            "type": "number"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "description": "The same amount converted to `base_currency`, still signed. Sum the magnitudes of these to reach `base_total_amount`; null when no FX rate covered the date."
      +      },
      +      "category": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "description": "Display label of THIS transaction's management category, not the group's. Null when uncategorized."
      +      },
      +      "category_key": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "description": "Stable taxonomy key of the same category — branch on this, never on the label. Null when off-catalog."
      +      },
      +      "currency": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ]
      +      },
      +      "date": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "description": "The day the transaction posts under (YYYY-MM-DD); null when it carries no date."
      +      },
      +      "description": {
      +        "anyOf": [
      +          {
      +            "type": "string"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "description": "The bank's remittance text — what distinguishes one line from the next. Null when the row carries none."
      +      },
      +      "id": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "id",
      +      "date",
      +      "description",
      +      "category",
      +      "category_key",
      +      "amount",
      +      "currency",
      +      "base_amount"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / rows / items / properties / transactions_omitted
      Added value: +{
      +  "description": "How many of the row's transactions the cap left out: `tx_count` minus the listed ones.",
      +  "maximum": 9007199254740991,
      +  "minimum": -9007199254740991,
      +  "type": "integer"
      +}
    • changedOutput schema / properties / rows / items / required
      Previous value: -[
      -  "id",
      -  "company_id",
      -  "name",
      -  "logo_url",
      -  "calendar_year",
      -  "calendar_month",
      -  "period_label",
      -  "tx_count",
      -  "base_total_amount",
      -  "mode",
      -  "suggested_action",
      -  "matched_provider_name",
      -  "matched_provider_has_blueprint",
      -  "matched_connector_service_id",
      -  "proof_task_id",
      -  "acquisition_status",
      -  "refusal_reason"
      -]New value: +[
      +  "id",
      +  "company_id",
      +  "name",
      +  "logo_url",
      +  "calendar_year",
      +  "calendar_month",
      +  "period_label",
      +  "tx_count",
      +  "transactions",
      +  "transactions_omitted",
      +  "base_total_amount",
      +  "mode",
      +  "available_modes",
      +  "suggested_action",
      +  "matched_provider_name",
      +  "matched_provider_has_blueprint",
      +  "matched_connector_service_id",
      +  "proof_task_id",
      +  "acquisition_status",
      +  "refusal_reason"
      +]
  10. Added

TDQS

A5/5.0
Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses extensive behavioral detail: one row per counterparty rather than per month, no batch endpoint and per-month cost, categorized-only coverage, a 25-row cap with transactions_omitted, mode/available_modes semantics, and a clear statement that it does not mint tasks or fetch invoices. This goes far beyond the annotation's safety signal.

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 long but densely organized into purpose, period naming, cost, output shape, per-row fields, modes, and side-effect guarantees. Every paragraph adds a distinct operational rule or edge case, and the core purpose is front-loaded in the first sentence. There is no filler or repetition.

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?

Given the tool's complexity, the description is complete enough to call it correctly: it covers period selection, output semantics, edge cases like dropped_groups and unknown categories, field presence conditions, caps, and the read-only guarantee. Even with an output schema present, the description supplies critical interpretation rules the schema cannot convey.

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 already 100%, but the description adds substantial meaning: period can be named one of several mutually exclusive ways, omitting it falls back to the user's period-card selection, each named month costs a separate read, and workspace resolution comes from the caller's authorized token. These semantics are not inferable from the schema alone.

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 states a precise verb, resource, and scope: it lists supplier invoices a past period is still missing from settled spend, one row per counterparty, matching the Well app's expense-invoices card. This clearly distinguishes it from sibling read tools like well_sum_invoices or well_list_unposted_transactions.

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?

It explicitly states when to use the tool ('which invoices am I missing for <month>?'), gives the exact input shapes, and describes refusal conditions (current/future months, adjustment period 13, duplicates, no period selected). It also tells the agent to request only the months the user named and to call the tool directly without prerequisites.

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