researchResearch a question under a USDC creator-payment budget. Keryx selects sources, pays access tolls and weighted citation rewards, then returns a grounded answer and receipt.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Optional Keryx model catalog id, for example deepseek-chat. | |
| budget | No | Maximum creator-payment budget in USDC; clamped to the caller's tier. | |
| question | Yes | Research question. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description discloses payment behavior and answer format, adding context beyond annotations (e.g., 'pays access tolls and weighted citation rewards'). No contradictions with 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 efficient sentences with front-loaded purpose. Every word adds value 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?
The description covers key aspects: action, budget mechanism, process, and output (answer and receipt). No output schema, but sufficient for agent selection.
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 description coverage is 100%, and the description adds meaning to the budget parameter by explaining its role in payments. No parameter documentation gaps.
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 action ('Research a question') and unique mechanism (USDC creator-payment budget, source selection, tolls and rewards), which distinguishes it from sibling 'keryx_status'.
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?
Implied usage: the tool is for research questions with a budget. No explicit when-to-use or when-not-to-use guidance, though sibling difference is clear.
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.
The two tools are highly distinct: keryx_status provides metadata about the server and caller, while research performs a complex research task. There is no functional overlap.
Both use snake_case, but keryx_status is a noun phrase (status check) and research is a bare verb (action). Minor inconsistency in verb_noun pattern, but both are clear and predictable.
With only 2 tools, the server feels minimal. While each tool has a clear scope, the small count may leave users wanting more (e.g., budget configuration, history). Borderline thin for a general-purpose server.
The server covers status and research, but lacks complementary tools like budget management, source listing, or result history. For a dedicated research assistant, these are notable gaps.