[SDK Docs] Search across the documentation to find relevant information, code examples, API references, and guides. Use this tool when you need to answer questions about Docs, find specific documentation, understand how features work, or locate implementation details. The search returns contextual content with titles and direct links to the documentation pages.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnlyHint=true, openWorldHint=true, and destructiveHint=false. The description adds useful behavioral context by noting the return format: 'The search returns contextual content with titles and direct links to the documentation pages.' This goes beyond the annotations without contradicting them.
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?
The description is two well-structured sentences. The first sentence states the core function and scope. The second provides usage guidance. No filler or redundant content. The '[SDK Docs]' prefix helps with scoping, and every sentence earns its place.
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 simple search tool with one required parameter, strong annotations (readOnly, openWorld, non-destructive), and no output schema, the description covers the essential context: what it does, when to use it, and what results it returns. There are no complex edge cases or hidden behaviors that need disclosure.
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 schema has a single parameter 'query' with no description (0% coverage). The description does not explicitly explain what the query parameter should contain, but the tool name and overall description imply it is the search text. Since this is a simple, self-evident parameter, the lack of explicit parameter guidance is a minor gap, hence a mid-range score.
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: 'Search across the documentation to find relevant information, code examples, API references, and guides.' The verb 'search' is specific, and the resource (documentation) is unambiguous. It also distinguishes from siblings like docs_getPage by positioning itself as the search tool for documentation.
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 gives explicit usage contexts: 'Use this tool when you need to answer questions about Docs, find specific documentation, understand how features work, or locate implementation details.' While it doesn't name alternative tools or when-not-to-use, the contexts are clear enough to guide selection among the docs tool family.
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.
Several tools have overlapping scopes: sodax_get_token_supply, sodax_get_total_supply, and sodax_get_circulating_supply all provide supply data, and the four money_market_* getters could be conflated. However, most tools are distinct and descriptions help.
The sodax_* tools follow a consistent get_<resource> pattern, but docs_* tools mix camelCase (getPage, searchDocumentation) with snake_case (list_tools), and there are non-get verbs like refresh and submit. This inconsistency makes the naming pattern less predictable.
With 40 tools, the server exceeds the 25-tool threshold for even a comprehensive API. Many endpoints are granular (e.g., separate supply tools) and could be consolidated, making the set feel bloated.
The tools cover a wide range of SODAX features: docs, money market, AMM, relay, solver, token data, and user positions. Missing are write operations (except relay_submit) and a few data endpoints like pool details, but for a query-oriented MCP it's largely complete.
