get_transaction_evidenceUse this when the user asks what happened in a specific transaction. Combines indexed Explorer transaction data, receipt data and live RPC fallback if available.
| Name | Required | Description | Default |
|---|---|---|---|
| txHash | Yes | 0x-prefixed transaction hash to inspect or resolve. |
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | Structured result data returned by the XGR MCP gateway. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral context: it combines indexed data with live RPC fallback if available, which is useful for understanding potential latency or data freshness. No contradiction.
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 sentences, front-loaded with use case, first sentence imperative. Every word earns its place; no filler.
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?
Given the tool has an output schema and annotations covering safety, the description sufficiently explains the tool's behavior (combining data sources, fallback) and when to use it. Minor gap: doesn't mention potential delays from RPC fallback, but overall complete.
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 100% for the single parameter txHash, which already includes pattern and description. The description does not add extra meaning beyond the schema, so a baseline of 3 is appropriate.
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 clearly states the tool's purpose: to answer what happened in a specific transaction by combining indexed Explorer data, receipt data, and live RPC fallback. It distinguishes itself from siblings like get_transaction_receipt by offering a more comprehensive 'evidence' output.
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?
It explicitly instructs when to use ('when the user asks what happened in a specific transaction') but does not mention alternatives or when not to use. However, the sibling tools suggest more specific queries, and the description implies this is the holistic option.
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.
There are many overlapping session-listing tools (list_xdala_sessions, get_recent_xdala_sessions, find_latest_xdala_session, list_xdala_session_ids, get_latest_session_payload) and duplicate validation tools (validate_xdala_bundle is an alias for validate_xgr_multibundle). Descriptions help but boundaries are still unclear.
The verb_noun snake_case pattern is consistent across nearly all tools (get_, list_, create_, cancel_, validate_). Minor inconsistencies include the alias validate_xdala_bundle and interchangeable verbs like get_ vs read_ vs resolve_ for similar read operations.
With 95 tools, this is far beyond the 25+ threshold for 'too many'. While the domain is broad, the sheer number makes the tool surface unwieldy and difficult for an agent to navigate.
The tool set covers a wide range of operations: handoffs, session queries, transaction exploration, contract reads, validation, gas requests, and purchases. Minor gaps exist (e.g., no direct workflow editing tools), but overall the surface is remarkably complete.