Skip to main content
Glama

List invoices whose posting stopped

well_list_halted_invoices
Read-only

List the invoices of one fiscal period that have no journal entry yet, each with the reason its posting stopped. These are exactly the invoices the close's unposted_invoices blocker counts: the invoice is in Well, and the posting did not book it. Use it to answer why that blocker holds. It is not the missing-invoice read: settled spend without an invoice is well_get_close_proof_gaps.

Each row has invoice_id, invoice_number, issue_date (YYYY-MM-DD), amount ({ amount, currency } or null), issuer_name, receiver_name, posting and reason. posting: "halted" means the latest posting attempt stopped; reason is its halt code as Well recorded it (for example missing_item_classification, neither_party_own, party_missing), and reasons lists every blocker code that attempt recorded. posting: "never_attempted" means Well has not tried to post it yet; reason is null. halted_at is when the latest attempt ran.

total is the size of the whole gap; truncated: true means the list shows fewer rows than total. An empty list with total: 0 means no invoice of the period is unposted.

The period is named in FISCAL terms. Take fiscal_year and fiscal_period from well_get_close_state or a well_list_periods entry; never derive them from a calendar month yourself.

status: "failed" means the read failed: the list is unknown, never empty.

When the token authorizes one workspace, call this directly — no workspace call is needed first. When it authorizes several, this read will not guess which one you mean: pass workspace_id on the call.

Input Schema

NameRequiredDescriptionDefault
limitNoHow many invoices to list, oldest issue date first, 50 by default.
fiscal_yearYesThe fiscal year of the period to read.
workspace_idNoTarget workspace. Omit when the token authorizes one workspace. Required when it authorizes several: this read reports one workspace's own figures and will not choose which.
fiscal_periodYesThe fiscal period, 1-12 for a month; 13 is the adjustment period and resolves to no rows.
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.
workspace_scopeNoRestrict this call to the family: the token's primary workspace plus the company workspaces under it that you are a member of. Unrelated authorized workspaces drop out of the read; row reads merge across the family, while a per-workspace figure still reports exactly one workspace.

Output Schema

NameRequiredDescriptionDefault
errorNo
totalNo
statusYes
successYes
invoicesNo
truncatedNo
fiscal_startNo
conversation_idNoThe conversation this result belongs to. Pass it back as the conversation_id argument on every later Well call in the same conversation.
newly_connectedNoTools that connected to this workspace since the last result and that no session was told about yet, oldest first. Present only when at least one tool is new. The connected-line rule says when to tell an entry; when it does, one line per entry, in the person's language: "<name> is connected.". Never fold several entries into one sentence. Each entry comes back once, on one result only: never repeat its line later.
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. Changed1 schema field changed
    • addedOutput schema / properties / fiscal_start
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "reason": {
      +      "const": "fiscal_start_unset",
      +      "type": "string"
      +    },
      +    "setup_instruction": {
      +      "type": "string"
      +    },
      +    "status": {
      +      "const": "held",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "status",
      +    "reason",
      +    "setup_instruction"
      +  ],
      +  "type": "object"
      +}
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only cover the read-only/no-destruct safety profile; the description adds substantially more: `posting` state semantics, example halt codes, the meaning of `total` vs `truncated`, that an empty list with `total: 0` is a genuine zero rather than a failure, and that `status: "failed"` means the list is unknown. That failure-vs-empty distinction is exactly the kind of context an agent cannot infer from annotations.

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 purpose, then exclusions, then row semantics, then failure semantics, then period sourcing, then workspace rules — a sensible order. The long middle paragraph restating row field names overlaps with the existing output schema, which is the only place the text spends more than it needs to.

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 filtered, paginated, multi-workspace read this covers everything that matters: how to source the required period parameters, how to interpret truncation, how to distinguish failure from empty, and how to handle single- vs multi-workspace tokens. Return values are additionally backed by an output schema, so nothing an agent needs to call it 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 earns above it by explaining that the period is FISCAL, not calendar, and by prescribing where to obtain the values. It does not discuss `limit` ordering or the `conversation_id`/`workspace_scope` interplay, which remain schema-only, so it is not a full 5.

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?

States a specific verb and resource with a precise scope: invoices of one fiscal period with no journal entry, each with its halt reason. It also ties itself to a named artifact (the close's `unposted_invoices` blocker) and explicitly disclaims the nearest sibling read (`well_get_close_proof_gaps` for settled spend without an invoice). An agent can pick it apart from `well_list_missing_invoices` and `well_list_unposted_journals` without opening a schema.

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?

Gives the triggering question ('use it to answer why that blocker holds'), names the alternative for the adjacent case, and specifies the prerequisite source for the period parameters (take `fiscal_year`/`fiscal_period` from `well_get_close_state` or a `well_list_periods` entry, never derive from a calendar month). Workspace calling rules are also stated (call directly with one workspace, pass `workspace_id` with several).

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