list_invoicesRetrieve recent crypto invoices newest first, filter by status, and paginate using a before timestamp to fetch earlier results.
Recent invoices, newest first. Filter by status; page with before (created_at of the last item).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| before | No | ISO timestamp: only invoices created before it | |
| status | No |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds genuinely useful behavior — newest-first ordering and cursor-style pagination keyed on created_at — but omits the default page size, the 100 cap, and whether results are a live window or a full history.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, no filler, with the ordering and scoping facts front-loaded before the paging instruction.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no explanation of what an invoice record contains or what happens when no filters are supplied, the agent must guess the default result size and the response shape. The ordering and pagination story is solid, but the return-side and default behavior gaps keep it at adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 33% (only `before` is documented), so the description must compensate. It does: it clarifies that `before` is the created_at of the last item (cursor semantics, not a generic date bound) and that `status` is a filter, which is real added meaning. The `limit` parameter is left unexplained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States the resource (invoices) and the ordering (newest first), which distinguishes it from get_invoice (single) and find_invoice_by_order. However, 'Recent' is unscoped — it doesn't say whether this is an unbounded list or a windowed set — and no sibling is named explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by explaining the filter and paging mechanics, but never says when to pick this over find_invoice_by_order or get_invoice. An agent can infer it is the browse/list path, but the routing guidance is left implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.