CortexCloud MCP

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

The description discloses the cost model ('Paid per call in USD via x402'), which is a useful behavioral trait. However, with no annotations provided, it does not mention whether the tool is read-only, any rate limits, or the format of the returned balance, leaving some behavioral aspects undocumented.

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, consisting of two short sentences. It front-loads the core purpose and adds the cost detail efficiently with 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 simple tool with one parameter and no output schema, the description provides enough context: what it does and that it costs money. However, it does not specify the return unit (e.g., wei vs. ETH) or whether any address validation is performed, which could be useful for the agent.

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 covers the only parameter 'address' with a description '0x address' (100% coverage). The description adds no additional meaning about the parameter, so the baseline score of 3 is appropriate.

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 the Base native ETH balance for an address, which specifies the resource and scope. It distinguishes from sibling tools like base_token_balance by noting 'native ETH' vs. tokens, but lacks an explicit verb like 'get' or 'retrieve'.

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 phrase 'Base native ETH' implies this tool is for native ETH on Base, not for tokens or other chains, but it does not explicitly state when to use this tool over alternatives like base_token_balance or eth_balance. No direct comparison or exclusion is provided.

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 burden of behavioral disclosure. It reveals that the tool is 'paid per call via x402,' which is useful cost-related information. However, it does not explicitly state that the operation is read-only, nor does it describe error behavior, slippage, or any side effects. The payment disclosure adds value but lacks other behavioral context.

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 sentence, 13 words, and immediately identifies the tool's purpose and network. It is front-loaded with the most critical information and contains no filler or repetition. It is appropriately sized for a simple tool.

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 provides enough to understand the core function and even notes the paid per-call aspect. However, it lacks any mention of the return format (e.g., raw wei or decimal-adjusted) or potential error conditions. Given the minimal complexity, this is moderately complete but still has gaps that could affect invocation.

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 input schema fully describes both parameters: token is 'Token contract address' and address is '0x address', giving 100% coverage. The description does not add additional meaning beyond restating that it is an ERC-20 token on Base. Baseline 3 is appropriate since the schema handles semantics adequately and the description adds minimal extra detail.

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 that this tool retrieves an ERC-20 token balance on the Base network for a given address. It differentiates from sibling tools like base_balance (likely native Base balance) and eth_balance (Ethereum) by specifying both the token type and network. This is a specific and unambiguous purpose.

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 no guidance on when to use this tool versus alternatives such as base_balance or eth_balance. It does not mention scenarios where one should prefer this tool, nor does it exclude any cases. There is no comparison with sibling tools or context for decision-making.

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. It discloses a key behavioral trait: the tool is paid per call in USDC on Base via x402, with a payTo wallet. This is useful context beyond what the name implies. However, it does not mention other behavioral aspects like default stream behavior, rate limits, or response format, leaving transparency partial.

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, tightly worded sentence that leads with the core function and adds only the essential payment context. There is no filler or redundant restatement of the tool name. It is appropriately sized for the information it conveys, making it highly concise and well-structured.

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 and no annotations, the description should provide more complete context about what the tool returns and how it behaves. It only covers the purpose and payment, leaving out details about the output format, optional parameters, and when to use it. For a tool with 5 parameters and 2 required, this is under-specified for an agent to reliably invoke it in varied scenarios.

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 only 40% (model and messages have descriptions), but the tool description adds no parameter information at all. It does not clarify the semantics of stream, max_tokens, or temperature, which are left undocumented in both the schema and description. Since coverage is below 50%, the description was expected to compensate but does not.

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 'OpenAI-compatible chat completions', which identifies the tool's function with a specific verb and resource. It doesn't explicitly contrast with sibling tools like 'responses' or 'embeddings', but the OpenAI-compatibility keyword gives a hint about the style and scope, earning a 4 rather than 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 gives no guidance on when to use chat_completions versus alternatives such as responses or image_generation. It only mentions the payment model, which is not a usage guideline. There is no mention of preferred use cases, exclusion criteria, or relationships to other tools, so this dimension is largely unaddressed.

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?

The description discloses a meaningful behavioral trait beyond the schema: the tool is paid per call in USD via x402. However, with no annotations provided, it omits other behavioral details such as rate limits, authentication requirements, or the nature of returned data.

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, consisting of two short sentences that convey the core function and a key cost-related behavior. Every word contributes value, with no fluff or 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?

For a simple one-parameter search tool with no output schema, the description adequately covers purpose and cost. It could be more complete by indicating what kind of data is returned, but the core usage context is sufficiently clear.

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 single 'q' parameter described as 'Search query'. The description adds little beyond the schema, reinforcing that the query targets crypto coins but providing no additional semantic detail such as formatting, allowed values, or examples.

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 a specific action ('Search crypto coins') and a query-based input, which distinguishes it from broader tools like web_search and dex_search. However, it does not explicitly differentiate from sibling tools like prices or dex_search beyond naming the resource type.

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 guidance is provided on when to use this tool versus alternatives such as dex_search or prices. The description implies its use for coin lookups by query but lacks any contextual clues, exclusions, or alternative tool references.

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. It explicitly discloses a critical behavioral trait: "Paid per call in USD via x402." This informs the agent that the call incurs a cost, which is essential for decision-making. It does not disclose other behaviors like rate limits or authorization, but the payment disclosure adds significant value beyond the schema.

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 exceptionally concise: two short sentences, front-loaded with the core purpose, followed by the payment note. Every word is purposeful with no 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?

With no annotations, no output schema, and only 33% schema coverage, the description must be self-sufficient. It is only two sentences and fails to explain the return format, the meaning of `vs`, or any error conditions. For a paid tool, this is insufficient for an agent to confidently invoke it without guessing.

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 only 33% (only `id` is described). The description adds meaning for `days` via "over N days," but it does not explain the `vs` parameter, which remains opaque. While some value is added, the description does not fully compensate for the low schema coverage, leaving a key parameter undefined.

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: "Coin price history over N days." This specifies the resource (coin price history) and the time dimension (N days), distinguishing it from sibling tools like `prices` which likely provides current prices.

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 phrase "over N days" implies use for historical price data, but the description does not explicitly state when to use this tool versus alternatives like `prices`, nor does it mention any exclusions or prerequisites. Usage is only implied, not clearly guided.

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 only discloses that calls are paid via x402 and that data includes OHLCV and categories. It omits response structure, pagination, rate limits, and data freshness, which are important behavioral traits for a paid API.

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, concise sentence that front-loads the core purpose ('Categorized DeFi protocols list'). Every word is meaningful, with no redundancy or filler. It maximizes information density in minimal space.

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 gives a minimal viable overview: it's a categorized list with OHLCV data and a payment requirement. However, it lacks details about the exact response format, how to interpret OHLCV for protocols, and the payment workflow. Since there is no output schema, the description should be richer to fully inform the agent, but it does cover the essential nature of the 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?

The schema has zero parameters, so the description adds nothing beyond the schema. The baseline for no parameters is 4, and the description correctly provides no parameter details because none exist. This is 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 clearly identifies the tool as a categorized list of DeFi protocols, mentioning OHLCV and categories. It implies a retrieval action and specifies the resource (DeFi protocols). However, it doesn't explicitly differentiate from sibling tools like defi_yields or dex_pairs, which are also DeFi-related, so it doesn't fully distinguish.

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 no guidance on when to use this tool versus alternatives. It doesn't mention any conditions, use cases, or contrast with sibling tools. An agent would have no basis to select this over defi_yields or dex_pairs from the description alone.

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 must carry the full transparency burden. It only discloses the paid-per-call aspect, but does not mention data freshness, the meaning of 'top pools', result limits, or any auth requirements. The behavioral characteristics are largely undisclosed.

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, consisting of two short sentences. Every word is relevant, and the payment note is important for cost-aware tool selection. No fluff or 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?

For a tool with no output schema and no annotations, the description should explain what the response looks like and clarify the scope of 'top pools'. It also omits that the protocol parameter is an optional filter. The sparse description leaves significant gaps for an agent to know what to expect.

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% and the 'protocol' parameter includes a helpful description ('Filter by project slug, e.g. aave'), so the schema already provides necessary semantics. The description adds nothing beyond the schema, so the baseline score of 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 the tool returns APY/TVL data for top DeFi pools, which is a specific and distinct purpose compared to sibling tools like defi_protocols, dex_pairs, or prices. The resource and data type are explicit.

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 guidance is provided on when to use this tool versus alternatives. The payment note ('Paid per call via x402') is a cost signal but does not explain use cases, when not to use it, or how it compares to related tools like defi_protocols or dex_pairs.

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?

The only disclosed behavior is the per-call payment via x402, which is valuable context. Without annotations, the description does not explicitly state whether the operation is read-only, its response format, or any side effects, leaving some gaps.

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 sentence with no redundancy; the payment note is essential and earns its place. It is front-loaded with the tool's purpose and remains appropriately sized.

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 lacks an output schema, so the description should clarify what 'DEX pair info' includes (e.g., price, liquidity). It does not, leaving a gap in return-value expectations. For a two-parameter tool, this is still a moderate omission.

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 documents both parameters at 100% coverage. The description's phrasing 'token address' mirrors the schema description, adding little new semantic meaning beyond what is already structured.

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 indicates the tool provides DEX pair information keyed by chain and pair address. It distinguishes the resource but does not explicitly contrast with dex_search, so a small gap remains.

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 when you have a specific chain and pair address, and the payment note suggests using it only when necessary. However, it offers no explicit guidance on when to prefer this over alternatives like dex_search or any exclusions.

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?

The only behavioral trait disclosed is that it is 'Paid per call in USD via x402', which is useful context about cost. However, with no annotations to provide safety hints, the description does not mention rate limits, query matching behavior, or whether results are paginated.

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 entire description is two short sentences, front-loaded with the primary purpose. Every word earns its place, and it is highly efficient.

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 simple (one parameter, no output schema), but with no annotations or output schema, the description should explain what results look like or how to interpret them. The cost disclosure adds value but does not cover all gaps expected for a search 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?

The schema already fully documents the single parameter 'q' as a 'Search query' (100% coverage). The description adds no extra meaning beyond the word 'query', so the baseline of 3 is appropriate.

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 'Search DEX pairs by query', using a specific verb and resource. The phrase 'by query' distinguishes this tool from the sibling 'dex_pairs', which likely lists all pairs rather than searching.

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 guidance is provided on when to use this tool versus alternatives like 'dex_pairs' or 'coins_search'. The description does not mention exclusions, prerequisites, or typical use cases.

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 discloses that calls are paid per use, which is useful, but it omits details about response format, authentication requirements, rate limits, or whether the operation is read-only. This leaves the agent uncertain about side effects and expected output.

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 short, purposeful sentences. The first states the core function, and the second adds essential cost information. No redundant words 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?

For a simple tool with no output schema and no annotations, the description is too sparse. It does not explain what the response contains (e.g., the embedding vectors), nor does it relate to sibling tools or mention system requirements. The 'OpenAI-compatible' hint is helpful but does not fully compensate for the missing context.

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 input schema already has 100% coverage with descriptions for both parameters. The description adds no extra meaning beyond what the schema provides, so it neither enhances nor degrades parameter clarity. Baseline of 3 is appropriate.

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 'text embeddings' and specifies it is OpenAI-compatible, indicating it generates vector representations. However, it lacks a verb like 'generate' or 'create', which slightly reduces clarity but still distinguishes it from other tools like chat_completions and models.

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 no guidance on when to use this tool versus alternatives such as chat_completions or responses. It does not mention use cases like semantic search or similarity, nor does it exclude other tools. It only states what it is and the payment mechanism.

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. It discloses that the tool is 'Paid per call via x402' and specifies the returned asset (native ETH). However, it does not describe response format, potential errors, or confirm read-only behavior, leaving some transparency gaps.

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, compact sentence that states the tool's purpose and payment model. Every word earns its place with no 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?

For a simple balance lookup tool with one parameter, the description covers the key context: the asset (native ETH), the chain (Ethereum mainnet), and the payment model. It falls short of fully specifying the response structure, but this is likely inferable. It is adequate given the tool's 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 input schema already describes the address parameter as '0x address' with 100% coverage. The description adds no additional meaning about the parameter, so the baseline of 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 identifies the tool as returning native ETH balance on Ethereum mainnet, distinguishing it from sibling tools like base_balance. However, it lacks an explicit verb like 'get' or 'fetch', making the action implicit rather than stated.

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 by specifying 'Ethereum mainnet' and 'native ETH', which implies when to use this tool over Base-chain alternatives. It does not explicitly name alternatives or exclusions, so it earns a 4 rather than 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?

No annotations are provided, so the description carries the full burden. It discloses the pass-through proxying behavior and the cost implication ('Paid per call via x402'). However, it does not mention response format, potential errors, rate limits, or network specifics. Some behavioral context is added, but it is not comprehensive.

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, focused sentence followed by a short billing note. It is front-loaded with the primary action and examples, with no superfluous information. This is optimal conciseness.

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 no output schema and the generic nature of an RPC proxy, the description lacks important context: supported methods, network selection, response structure, and usage guidance relative to specialized siblings. It is not complete enough for an agent to fully understand the tool's capabilities and constraints.

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 only 50% (method and jsonrpc have descriptions, id and params do not). The description does not clarify the meaning of 'id' or 'params' beyond the JSON-RPC context. Since the parameters are not explained in the description, the agent may not know their exact format or required values, and the description does not compensate for the schema 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 it as a proxy for Ethereum JSON-RPC calls, with examples of specific methods. This makes the tool's purpose very clear and distinguishes it from specialized sibling tools like eth_balance, which focus on single operations. The phrase 'Proxy an Ethereum JSON-RPC call' is a specific verb+resource construction.

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 no guidance on when to use this generic proxy versus the specialized sibling tools (e.g., eth_balance). It does not mention exclusions, alternatives, or prerequisites. Although 'Paid per call via x402' warns about cost, it does not help the agent decide when this tool 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?

No annotations are provided, so the description carries full burden. It discloses that the tool is paid ('Paid per call in USD via x402'), which is useful behavioral context. However, it does not mention response format, pagination, or potential limits, though for a simple zero-parameter list tool this may be sufficient.

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 short sentences that are front-loaded with the core purpose ('List supported fiat currencies/rates') followed by the payment caveat. Every word contributes meaning; no waste.

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 zero-parameter tool with no output schema, the description adequately covers the essential behavior: what the tool does and that it costs money. It does not explicitly clarify the exact return structure (whether rates are included), but the phrase 'currencies/rates' gives a reasonable expectation.

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 tool has zero parameters, and the schema coverage is 100% (vacuously). The description adds no parameter-specific information because none is needed. Baseline 4 applies for 0 parameters.

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 'List supported fiat currencies/rates' with a specific verb and resource. It distinguishes from sibling fx_price (which likely gets a specific price) by focusing on listing the supported set rather than performing conversions.

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?

Usage is implied by the description: if you need a list of supported fiat currencies, use this. However, there is no explicit comparison with alternatives like fx_price, and the payment note 'Paid per call in USD via x402' is about cost, not selection 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?

With no annotations provided, the description carries the full burden. 'Paid per call via x402' discloses a significant cost behavior, which is valuable. However, other behavioral traits like read-only nature, data freshness, or error conditions are not mentioned, though the simplicity of the tool mitigates the need.

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, using only two short clauses to convey the tool's purpose and a critical caveat. Every word earns its place, 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?

For a simple two-parameter tool with no output schema, the description reasonably covers the core function and cost. The lack of explicit return format is mitigated by the term 'FX rate', which clearly implies a numeric exchange rate. The paid-per-call warning adds important operational context.

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 input schema already provides descriptions for both parameters ('base' default USD, 'quote' default EUR) with 100% coverage. The description adds no additional semantic meaning beyond the schema, so the baseline of 3 is appropriate.

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 'FX rate between two currencies' clearly indicates a specific resource (FX rate) and an implied operation (get/retrieve). It is concise but does not explicitly differentiate from sibling tools like 'prices' or 'fx_list', though the mention of 'between two currencies' suggests a focused pairing tool.

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 guidance is provided on when to use this tool versus alternatives like 'fx_list' or 'prices'. The only additional note, 'Paid per call via x402', implies a cost consideration but does not explain if this should be avoided for high-volume queries or when a cheaper alternative exists.

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 of behavioral disclosure. It discloses the cost model ('Paid per image in USD via x402'), which is a useful behavioral trait, but omits other important behaviors such as authentication requirements, rate limits, output format, or any side effects. The disclosure is minimal.

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, consisting of two short sentences that each serve a purpose: stating the function and noting the cost. There is no fluff or redundancy, making it well-structured for quick scanning.

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 has no annotations, no output schema, and a sparse input schema. The description provides only a bare function statement and cost note, lacking any additional context about parameters, output, or usage scenarios. This is completely inadequate for a 3-parameter tool with such minimal structured metadata.

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 only 33% (only 'n' and 'size' have descriptions, 'prompt' has none). The tool description does not compensate by explaining any parameters, including what 'prompt' should contain or how 'size' affects generation, leaving the agent without crucial semantic information.

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 function as 'AI image generation', which is a specific verb+resource. It does not explicitly distinguish from sibling tools, but the siblings are predominantly text/chat/crypto tools, making image generation inherently distinct. However, it lacks explicit differentiation phrasing.

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 no guidance on when to use this tool versus alternatives. It mentions payment but does not state any use cases, prerequisites, or exclusions, leaving the agent to infer context from the tool name and siblings.

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. It discloses that the tool is free ('no payment') and that it lists models, implying a read-only operation. However, it does not describe the response format, pagination, or any rate limits, leaving gaps in transparency.

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 sentence: 'List available AI models (free, no payment).' It is concise, front-loaded with the verb, and every word adds value.

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 parameters and no output schema, the description needs to convey what the tool returns. 'List available AI models' adequately implies a list of model identifiers or names. For a zero-parameter listing tool, this is sufficient; more detail would be nice but not essential.

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 tool has zero parameters, so the schema provides no room for ambiguity. The description adds no parameter information, but that is unnecessary since no parameters exist. Baseline 4 is appropriate.

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 uses a specific verb 'List' and resource 'available AI models', clearly stating what the tool does. It distinguishes from sibling tools like chat_completions and embeddings that consume models rather than enumerate them.

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 no explicit when-to-use guidance or alternatives. However, the context implies that this tool should be used to discover which models are available before calling model-consuming tools like chat_completions. This is only implied, not stated.

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 full burden. It discloses the external provider (Exa) and the cost ($0.02 per call via x402), which is important behavioral context. However, it does not state whether the operation is read-only, how results are returned, or what happens if no news matches, leaving some ambiguity.

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 sentence that is front-loaded with purpose and includes the critical cost detail. Every word earns its place, and there is no fluff or 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?

For a simple 2-parameter tool with no output schema, the description conveys the core purpose and cost. However, it omits the meaning of 'limit', the return format, and any mention of the query parameter's role, leaving notable gaps. These are partially mitigated by the tool's simplicity and the schema's basic parameter descriptions.

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 input schema describes 'q' with an example but 'limit' has only type and constraints. The description adds no parameter information, so an agent must infer that 'limit' means maximum news results and does not understand how it interacts with the query. Schema coverage is only 50%, and the description does nothing to compensate.

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 the tool provides 'Recent finance/crypto news via Exa', which clearly identifies the resource and domain. While it lacks an explicit verb like 'fetch' or 'search', the name and context imply retrieval, and it distinguishes itself from siblings like web_search and search_contents by being specifically about finance/crypto news.

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?

There is no guidance on when to use this tool versus alternatives. The description does not mention any exclusions, prerequisites, or comparisons to sibling tools like web_search or search_contents, so the agent receives no usage direction.

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?

The description discloses a significant behavioral trait: it is paid per call in USD via x402. However, with annotations absent, other behavioral details such as rate limits, response format, or error handling are not addressed. For a simple price tool, the cost disclosure adds some value but not complete transparency.

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 entire description is two short sentences, both of which are informative: one covers purpose and the other covers cost. It is perfectly concise and front-loaded with the core purpose.

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 clear schema and only two parameters, the description provides adequate context. The lack of an output schema is mitigated by the fact that the purpose ('prices') clearly implies return values, and the payment note adds important usage context.

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 input schema already provides 100% coverage with descriptions for both parameters. The description's mention of 'by coin id' merely aligns with the schema's ids parameter and does not add additional meaning beyond what is already documented.

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 providing crypto prices by coin id, which distinguishes it from sibling tools like crypto_history (historical data) and fx_price (forex). However, it lacks an explicit verb like 'retrieves' or 'gets', making it slightly less direct.

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 guidance is provided on when to use this tool versus alternatives. The mention of payment per call is a cost consideration but not a selection criterion, and no exclusions or comparisons are offered.

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. It does disclose a key behavioral trait—paid per call in USDC via x402—which helps cost awareness. However, it gives no information about return format, side effects, or whether it is a read/write operation. 'Alias of chat' is too vague to convey meaningful 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?

The description is short and front-loaded, but the first segment is a fragment, not a sentence. It contains only two pieces of information (alias and payment), both potentially useful, yet the overall brevity is a symptom of under-specification rather than intentional conciseness.

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?

This is a 4-parameter tool with no annotations, no output schema, and zero description coverage of parameters. The description does not help an agent understand the expected input format, output structure, or edge cases. It is far too sparse for the tool's complexity.

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 0%, and the description provides no parameter information. It does not clarify the meaning of 'model', 'input', 'temperature', or 'max_output_tokens'. The schema offers only names and types, which is insufficient for an agent to construct a valid call.

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 reads as a label ('OpenAI Responses API') rather than a verb-based action. It offers 'alias of chat' as a vague anchor but does not state what the tool actually does (e.g., generate completions). This fails to clearly distinguish it from siblings like chat_completions or embeddings.

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?

There is no explicit guidance on when to use this tool versus alternatives. The phrase 'alias of chat' hints at a relationship to chat_completions but does not name it or explain the difference. No when/when-not conditions are provided.

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 full burden. It discloses that the tool is paid via x402, which is a significant behavioral trait. However, it does not mention what happens for invalid IDs, whether the operation is purely read-only (though 'fetch' implies so), or any rate limits or failure modes. It provides some context but misses important behavioral 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 extremely concise, two sentences with no unnecessary words. Both sentences serve a purpose: the first states the core function, the second adds essential payment information. It is front-loaded and highly scannable.

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 has 3 parameters, no output schema, and no annotations. The description fails to explain what the response looks like, what the 'text' and 'summary' parameters do, or any prerequisites. The payment note is helpful but not sufficient to make the description complete for an agent to effectively use the 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?

The schema description coverage is only 33% (only 'ids' has a description). The tool description does not compensate; it does not explain the 'text' or 'summary' boolean parameters at all. The only parameter clarification is redundant with the schema ('Exa result IDs'). The description adds minimal semantic value beyond the schema.

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 fetches full content for Exa search result IDs, using a specific verb ('Fetch') and resource ('full content for Exa search result IDs'). This distinguishes it from sibling tools like web_search or news, which focus on searching, and implies a follow-up operation.

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 no guidance on when to use this tool versus alternatives. It does not mention that it should be used after a search, nor does it explain when to prefer it over other tools. The payment note is the only context, but it doesn't clarify usage scenarios.

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 full responsibility for behavioral disclosure. It does reveal a significant behavior—paid per call via x402—but lacks other critical details such as output format (e.g., audio file or base64), latency, rate limits, or side effects. The description adds limited value beyond the name and schema.

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 with no wasted words: 'Text-to-speech audio generation' and 'Paid per call in USD via x402.' It is front-loaded and every word contributes value, making it highly concise and well-structured.

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 no output schema and no annotations, the description is too sparse. It fails to explain what the agent actually receives (e.g., audio data, URL, file path) or any usage limitations. While the tool is simple, the description lacks enough context for an agent to select and invoke it confidently.

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 describes 'input' and 'model' but leaves 'voice' undocumented. The description itself does not clarify any parameters or provide additional meaning beyond the schema. With 67% schema coverage, the description should compensate for gaps, but it offers no parameter-related guidance.

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 'Text-to-speech audio generation' which clearly identifies the tool's function with a specific resource. However, it does not differentiate from sibling tools like image_generation or chat_completions beyond the obvious name, so it lacks direct sibling differentiation.

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 no guidance on when to use this tool versus alternatives. The only additional note is 'Paid per call in USD via x402,' which is a cost warning but not a usage guideline. No exclusions, alternatives, or contextual triggers are mentioned.

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 full transparency burden. It discloses a key behavioral trait—cost per query paid in USDC via x402—but does not mention output format, rate limits, or authentication requirements beyond payment.

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 short sentences, front-loaded with the primary purpose and a critical payment detail. Every word earns its place and there is no 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?

With no output schema and sparse annotations, the description leaves return format, filtering behavior, and use-case context unexplained. The payment note is useful but insufficient for a tool with five parameters and ambiguous output.

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 40%, and the description adds no parameter-specific meaning. It does not explain the type enum, domain filters, or numResults default, so it fails to compensate for the largely undocumented parameter schema.

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 identifies the tool as 'Web search' with provider 'Exa AI', which clearly states the action and resource. However, it does not explicitly distinguish this from sibling search tools like search_contents or news, so it misses some differentiation.

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 when-to-use guidance or alternatives are provided. The only operational note is the payment mechanism, which does not help an agent decide between this and similar search tools.

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