hyperliquid-mcp

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full disclosure burden. It successfully notes critical authentication requirements ('Requires EIP-712 signature'), but omits other necessary behavioral traits: idempotency characteristics, failure modes, confirmation requirements for high-value transfers, and the destructive/non-destructive nature of operations like 'cancel orders'.

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 appropriately sized with clear structure: purpose statement, authentication warning, and bulleted capability list. The em-dash and bullet formatting aid readability. The 'Request body (string)' schema description is tautological, but that's in the schema rather than the description text.

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 high complexity (multi-operation trading endpoint with cryptographic auth) and complete lack of output schema, the description omits critical information: expected response format, error handling patterns, rate limiting behavior, and the actual structure required for the opaque 'body' parameter. For a tool handling financial transactions, this completeness gap is significant.

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% (baseline 3). The description adds semantic context by listing supported operations (place orders, transfers, etc.), implying the body contains operation-specific payloads. However, it fails to compensate for the opaque 'body' parameter—no JSON structure, field requirements, or operation-type discrimination is documented, leaving the actual input format undocumented.

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 identifies the tool's purpose with specific verb ('Execute') and resource ('exchange operations'), and lists concrete capabilities (place/cancel orders, transfers, vault management). It effectively distinguishes from sibling 'query_info' by emphasizing mutation operations vs. read operations, though 'exchange' could be more precise (trading vs. currency exchange).

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 positions this as a 'Unified endpoint for all trading and account operations,' providing implicit guidance on scope. However, it lacks explicit when-to-use guidance relative to 'query_info' and does not state prerequisites like prerequisite wallet connections or when batching multiple operations is preferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It successfully discloses the unified/polymorphic nature of the endpoint and the type-field dispatch mechanism, but fails to declare safety properties (idempotent, read-only), auth requirements, rate limits, or response format details.

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 logically structured with a general statement, mechanism explanation, and bulleted list of query types. The first sentence contains slight redundancy ('Query information endpoint' followed by 'Unified endpoint for querying'), but overall it is appropriately sized with no waste in the bullet list.

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 complexity of a polymorphic unified endpoint, the description adequately covers the input capabilities (what can be queried) but omits operational context required for a query tool lacking annotations: response format variations by type, pagination behavior, authentication scope, and rate limiting. No output schema is present to compensate.

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?

Despite 100% schema description coverage (the 'body' parameter has a description), the schema only states 'Request body (string)'. The description adds crucial semantic value by explaining that this string should contain a 'type' field and detailing the specific query categories available, which the schema does not capture.

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 identifies the verb (Query) and resource (information), and comprehensively lists supported query categories (Market, User, Account, Staking data). However, it does not explicitly differentiate from sibling 'execute_exchange' (though implied by 'Query' vs 'Execute'), falling short of a 5.

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 explains the polymorphic mechanism ('type' field determines what data is returned) and lists available query types, providing implicit guidance. However, it lacks explicit 'when to use' rules, prerequisites, or explicit contrast with the execute_exchange alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.