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

With no annotations provided, the description must convey behavior itself. It explains what data is returned (mid prices) and the optional filtering, but it doesn't disclose response format, potential errors, or any limitations beyond that. For a simple read operation, this is adequate but not thorough.

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 extremely concise: three short sentences that communicate the core function, optional filtering, and performance trait. No wasted words, and the most important information is front-loaded.

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 tool with one optional parameter and no output schema, the description provides sufficient context: what it returns, how to filter, and a hint about speed. It lacks explicit details on response structure or edge cases, but these are likely inferable for a price-checking API. Overall, it's nearly complete for its simplicity.

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 already provides a clear description for the 'coins' parameter (comma-separated symbols, empty means all markets). The tool description repeats this but adds a concrete example ('BTC,ETH,SOL'). Since schema coverage is 100%, the description adds marginal value, keeping it at baseline.

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 returns current mid prices for all Hyperliquid markets, which is a specific resource and action. It also differentiates from siblings like get_perp_markets or get_market by emphasizing the 'mid price' focus and broad market coverage.

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 provides clear context for use: 'Fast way to check live prices' and optional filtering by coins. While it doesn't explicitly mention alternatives or exclusions, the purpose is well-scoped and the filtering guidance is useful.

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, the description carries the burden of disclosing behavioral traits. It mentions that the average is over the window, which adds a computation detail, but it does not disclose authentication requirements, rate limits, or response format. The read-only nature is implied by the name 'get' but not explicit.

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 sentences, front-loaded with the core function and followed by a usage note. No superfluous phrasing or repetition.

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 read-only tool with no output schema, the description covers the main purpose and return value (history plus average). It lacks specifics about the response shape (e.g., array of {time, rate}) but is sufficient for an agent to understand what it will receive.

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% with clear parameter descriptions. The description provides an example (BTC) and ties the average to the window, but adds no additional semantics beyond what the schema already documents.

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 as returning recent funding-rate history for a Hyperliquid perp, with an example coin and the average over the window. This distinguishes it from sibling tools like get_all_mids, get_order_book, and get_user_state, which serve different market-data purposes.

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 states usefulness for carry/basis and funding-trend analysis, giving users a clear context for when to use it. However, it does not name alternative tools or describe when not to use it, so it stops short of the highest score.

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, the description carries the burden of behavioral disclosure. It effectively communicates the read-only nature via 'snapshot' and lists the returned metrics, but it does not mention error behavior for invalid coin symbols, rate limits, or exactly how the response is structured.

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 a single, information-dense sentence with a clear subject and a colon-delimited list of included data. It is front-loaded with the main purpose and contains 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?

For a simple read tool with one parameter and no output schema, the description adequately enumerates the return fields (prices, 24h change, funding, open interest, premium, max leverage). It could explicitly state the response format (e.g., a single object) or error cases, but it is largely 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%, with a clear description and examples for the 'coin' parameter. The tool description repeats the example (BTC) but adds no new semantic info, so it matches the baseline for high coverage.

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 provides a 'detailed snapshot of a single Hyperliquid perpetual market' and enumerates the specific data fields (mark/oracle/mid price, funding, open interest, etc.). This distinguishes it from siblings like get_all_mids and get_perp_markets, which likely offer broader but shallower data.

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 implies use when you need deep data on one specific market by coin symbol, contrasting with list-style tools. However, it does not explicitly name alternatives or state when not to use this tool, so it falls short of a 5.

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 explains it is live, L2-level, and includes spread—critical behavioral details. However, it does not disclose potential limitations such as error handling or rate limits, so it is not fully transparent.

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 focused sentences with the main function front-loaded and no redundant text. Examples are integrated efficiently, making the description easy to parse.

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?

Despite lacking an output schema, the description explicitly enumerates the return content (top bids/asks with sizes and spread) and supported market types. For a tool of this simplicity, this is sufficient and 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 description coverage is 100% since both coin and depth have descriptive text and examples. The description's coin example duplicates the schema's example, adding no extra meaning. Therefore baseline 3 applies.

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 it provides a live L2 order book with top bids/asks, sizes, and spread. It distinguishes itself from sibling tools that cover mids, market metadata, funding, or user state, making the tool's specific purpose unmistakable.

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 gives clear usage context by specifying it works for perps and spot pairs with concrete examples, but it does not explicitly compare with alternatives like get_all_mids or get_market. Thus it lacks explicit when-not-to-use guidance.

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?

No annotations are provided, so the description carries the full transparency burden. It discloses read-only behavior implicitly through 'Overview' and 'get', and mentions sort options. However, it does not describe the response format (e.g., array of objects) or any potential behaviors like pagination, rate limits, or default sorting (though schema covers default). This is adequate but not rich.

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 concise, consisting of two sentences that front-load the primary purpose and then list key details (fields and sort options). Every sentence adds value with no redundancy or 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?

With no output schema, the description should convey what is returned. It lists the key market metrics, which effectively describes the output fields. However, it does not explicitly state the return type (e.g., array of market objects) or clarify units (e.g., funding rate annualized). This is a minor gap for an otherwise simple tool.

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% for both parameters, with clear descriptions for 'sort' (ranking metric, default 'volume') and 'limit' (how many to return, default 20). The description only restates the sort options and does not add new meaning beyond the schema, so baseline 3 applies.

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 this tool provides an overview of all Hyperliquid perpetual markets and enumerates the specific metrics included (mark price, 24h change, volume, open interest, funding rate, max leverage). It distinguishes itself from siblings like get_spot_markets and get_market by specifying 'perpetual markets' and 'all' markets.

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 implies usage for getting a broad market overview but does not explicitly contrast with alternatives like get_market for a single market or get_funding_history for funding history. No explicit 'when to use' or exclusions are given, leaving the context to be inferred.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals the tool is a read-only market overview by describing returned data fields, which implies non-destructive operation. However, it does not mention potential latency, authentication requirements, or clarify that 'gainers' and 'losers' likely sort by price change (a subtle behavioral nuance). The description covers the main surface behavior but lacks deeper caveats.

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 sentences, front-loaded with the core purpose ('Overview of Hyperliquid spot markets') and immediately specifies included tokens and data fields. It then lists sort options, which directly mirrors the schema. Every sentence provides useful information with no filler or repetition.

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 tool is a straightforward read-only market overview with no output schema or nested objects. The description includes the key output fields (price, 24h change, 24h volume, market cap) and sort behavior, which is sufficient for basic use. It could be more explicit about the default sort order and whether all spot markets are always included, but overall it delivers the necessary context for a simple tool.

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%: both parameters (sort and limit) have descriptive text and the sort parameter has an enum. The description repeats the sort options but does not add meaning beyond the schema—e.g., it does not clarify how 'change' differs from 'gainers/losers' or whether sort order is ascending/descending. Since the schema already provides adequate detail, the description adds no additional param semantics.

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: it provides an overview of Hyperliquid spot markets, listing specific token categories (HYPE, PURR, HIP-1 tokens) and the data fields returned (price, 24h change, volume, market cap). It distinguishes itself from sibling tools like get_perp_markets by explicitly targeting spot markets, making the purpose and scope unambiguous.

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 implies when to use this tool (when needing spot market overview data) and differentiates from perpetual markets by saying 'spot markets'. It does not explicitly name alternatives or state when not to use it, but the context is clear enough for an agent to select it over get_perp_markets for spot data. The sort options provide further usage context.

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?

Annotations are absent, so the description carries the transparency burden. It clearly identifies a read-only account-state query and details the returned fields (account value, margin, positions), but omits any mention of authentication, rate limits, or error behavior.

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?

Single front-loaded sentence that names the tool's purpose and enumerates key returned data without fluff. No wasted words.

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, no-output-schema tool, the description sufficiently covers input (wallet address), output structure (account balances and full position details), and scope (any Hyperliquid perp account). No significant gaps.

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?

With 100% schema coverage (address described as 'Wallet address, 0x...'), the description adds little beyond confirming 'any Hyperliquid wallet address' and the 0x format; schema already covers semantics.

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?

Description uses specific verb 'get' and names resource 'Perp account state' for 'any Hyperliquid wallet address', and enumerates fields. This distinguishes it from sibling market-data tools such as get_all_mids and get_order_book.

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?

No explicit when-to-use or alternative guidance is provided, though the account-state focus clearly differentiates it from market-data siblings. Usage context is implied but not stated.

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