compare_vaultsCompare two to five current vault records side by side using the same timestamped fields. It does not choose a winner or allocate capital.
| Name | Required | Description | Default |
|---|---|---|---|
| vaults | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint, idempotentHint, and destructiveHint=false. The description adds meaningful behavior beyond that: it compares rather than decides or acts, uses 'current vault records,' and restricts to 'the same timestamped fields.' This is sufficient context for a safe read-only operation.
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 tight sentences. The core action and scope are front-loaded, and the clarifying non-goal follows without redundancy. 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 one-parameter, read-only tool with an existing output schema and safe annotations, the description covers the essential invocation context: what is compared, how many, and what it does not do. It could slightly improve by specifying the expected vault identifier format or time semantics, but nothing critical is missing for selecting and invoking it.
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 description coverage is 0%, but the description directly compensates by explaining the vaults parameter's cardinality ('two to five') and its semantic type ('current vault records'). It still does not specify the exact string format (e.g., vault address vs. name), so it leaves a small gap, but for a single-parameter tool this is mostly adequate.
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 states a specific verb ('Compare'), a clear resource ('Hyperliquid vault records'), and an explicit scope ('two to five current vault records side by side'). It also disambiguates from sibling tools by stating it 'does not choose a winner or allocate capital,' making its purpose distinct from tools like rank_vaults.
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 clearly communicates the intended use case: side-by-side comparison of a bounded set of vaults. It adds non-goals ('does not choose a winner or allocate capital') to prevent mis-selection, though it does not explicitly name an alternative tool for ranking or allocation.
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.
Most tools target distinct actions and resources, but search_vaults and rank_vaults both return ordered vault lists, and fetch and get_vault can retrieve similar single-record data. The descriptions provide enough context to disambiguate in most cases.
Tool names generally follow a clear verb_noun snake_case pattern (compare_vaults, get_vault, rank_vaults). Standalone verbs like fetch and search are minor deviations but remain readable and consistent in style.
Nine tools is well-scoped for a research-focused server. Each tool covers a distinct investigation workflow without redundant entries or excessive surface area.
The server covers discovery, retrieval, comparison, ranking, risk explanation, alerts, and HLP-specific metrics. Minor gaps exist, such as no historical/time-series tool, but core research workflows are fully supported.