Look up a MERX invoice. Shows amount, recipient, token, and status. Agent must sign and broadcast the transfer separately (non-custodial).
| Name | Required | Description | Default |
|---|---|---|---|
| invoice_id | Yes | Invoice UUID (e.g. eaa00c4e-1234-5678-90ab-cdef12345678) returned by create_invoice, or a full payment URL containing /pay/<uuid>. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only and idempotent behavior. The description adds the non-custodial aspect, requiring separate signing and broadcasting, which is valuable context beyond the annotations.
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 concise sentences front-load the action and provide essential return information without redundancy.
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?
For a single-parameter lookup with no output schema, the description adequately covers the return fields and the non-custodial caveat, making it complete in context.
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?
The input schema already provides a detailed description with an example and format alternatives, achieving 100% coverage. The description adds no further parameter-specific meaning.
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?
The description uses the specific verb 'Look up' with the resource 'MERX invoice' and lists the displayed fields, clearly distinguishing it from creation and payment tools in the sibling list.
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 the tool is for retrieving invoice details but does not explicitly state when to use it instead of related tools like pay_invoice or create_invoice, nor any exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
With 66 tools, there is notable overlap between pricing tools (get_prices, get_best_price, compare_providers, get_price_history), balance/account tools (get_balance, get_account_info, get_trx_balance, get_trc20_balance), and order tools (get_order, list_orders, get_standing_order, list_standing_orders). While descriptions differentiate them, the sheer number and aliases (e.g., estimate_transaction_cost with 5 aliases) create ambiguity and potential for misselection.
Naming is mostly consistent using snake_case (e.g., create_order, approve_trc20). However, there is variation in verb placement: some start with verbs (create_order, get_balance) while others with nouns (agent_status, resource_broadcast). Patterns like wait_for_delegation break the simple verb_noun structure, but overall the style is uniform.
66 tools is far beyond typical MCP server sizes (3-15). While the domain is complex, many tools are utilities (convert_address, validate_address, explain_concept) that could be combined or omitted. The high count suggests scope creep and may overwhelm agents.
The server covers core workflows (buy resources, transfer tokens, check balances, create monitors/standing orders) but has notable gaps: order cancellation is missing (no cancel_order), many entities lack update/delete (e.g., invoices, monitors have cancel but no update), and execute_intent is not fully wired. Still, the surface is reasonably complete for its stated purpose.
