BTC, ETH, XRP, ONDO and TZ SELECT 4H market decisions with evidence and x402 purchase links.
Scored across 8 tools
Six of the eight tools (prepare_4h_setup_purchase plus the five asset-specific prepare_*_purchase tools) perform the same operation with nearly identical descriptions, so an agent cannot reliably tell whether the generic tool differs from the specific ones or which to call. Only discover_4h_setups and get_performance_evidence stand clearly apart.
All names are snake_case, verb-first (discover_, get_, prepare_), and the five asset-specific tools form a tight prepare_<asset>_4h_purchase pattern. The generic prepare_4h_setup_purchase places '4h' before the noun while the others place it after, a minor deviation only.
Eight tools is a well-scoped number for discovery, evidence, and purchase preparation. However, five near-identical per-asset variants inflate the surface more than the domain strictly requires, since a single parameterized prepare tool could cover them.
Discovery, evidence, and purchase preparation are covered, but there is no tool to retrieve setup content or signal entitlement after purchase, and no way to check current selection/assignment status beyond static discovery. Agents will hit a dead end once a purchase is authorized.
List the four independently purchasable market setups and TZ SELECT, which selects at most one of those setups per 4H cycle.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely new domain behavior — that TZ SELECT selects at most one setup per 4H cycle — but says nothing about the shape or ordering of the returned list, which matters for a discovery tool.
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?
A single sentence with no filler, front-loading the primary list behavior and then qualifying TZ SELECT. Every clause carries information.
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 zero-parameter read-only discovery call, the description is close to sufficient, but with no output schema an agent still doesn't know what each listed entry exposes (identifiers, 4H cycle timing, pricing) or that entries map one-to-one onto the prepare_*_purchase siblings.
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 takes zero parameters and the schema is fully closed (additionalProperties: false), so there is nothing for the description to disambiguate. Baseline 4 applies for a parameterless tool.
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?
States a specific verb (list) and resource (market setups), and adds a second named item (TZ SELECT). The phrase 'independently purchasable' implicitly links the returned items to the prepare_*_purchase siblings, though the four setups are never named outright.
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 only implied: an agent can infer this is the catalog to consult before calling prepare_4h_setup_purchase or a specific asset's purchase tool, but the description never says so or excludes any alternative. No explicit when-to-use or when-not-to-use is present.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the current public live-simulation evidence for closed setups selected by Trading Zones Selector. The rate does not describe every non-selected market package.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds that the evidence is "public" and from "live-simulation" (i.e., simulated rather than realized performance), which is genuinely useful context, but says nothing about freshness, volume of results, or what a caller receives.
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 short sentences with the scope statement front-loaded, so it is efficiently sized. However, the trailing caveat about "non-selected market packages" is cryptic and consumes space without adding usable information.
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 (no params, read-only) but has no output schema, so the description is the only source for what "evidence" and "rate" actually contain — and it leaves that undefined. Adequate to know it is a safe read, insufficient to know what comes back.
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 takes zero parameters, so the baseline is 4; there is nothing for the description to disambiguate. No parameter-related omissions exist.
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?
It has a clear verb ("Read") and names the source ("evidence ... selected by Trading Zones Selector"), but the key noun "evidence" and its "rate" are never defined, so the agent cannot tell concretely what is returned. It does not differentiate itself from the sibling prepare_*/discover_* tools, which makes the purpose only marginally distinguishable.
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 statement of when to call this versus the purchase-preparation or discovery siblings. The second sentence ("The rate does not describe every non-selected market package") reads as a disclaimer about interpreting results, not as guidance on invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the exact paid resource URL, price ceiling and wallet steps for one complete setup. The wallet-enabled agent signs and retries the returned HTTPS request; this tool never moves funds.
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | BTC, ETH, XRP or ONDO, or TZ-SELECT for the selector's current choice. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already say readOnlyHint=true, and the description usefully adds that 'this tool never moves funds' and that signing/funding happens outside the tool. That clarifies the two-step flow and the boundary of tool responsibility, which is real value beyond the annotations. It stops short of describing the price ceiling semantics or what happens if the returned request expires.
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 compact sentences, front-loaded with the outputs returned and followed by the execution model. No filler and nothing redundant with the schema or annotations.
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 does tell the agent what comes back (URL, price ceiling, wallet steps) and who acts next (the wallet-enabled agent). The main gap is the absence of any routing signal versus the six per-asset sibling prepare tools, which matters given how similar they are.
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 symbol enum is fully documented in the schema, including the TZ-SELECT meaning, so the description need not repeat it. Baseline 3 is appropriate since the description adds no extra meaning about the symbol parameter.
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?
States a specific verb (return) and concrete artifacts (paid resource URL, price ceiling, wallet steps) for one setup, which is far more informative than the title alone. However, it never explains how this generic tool differs from its near-identical siblings prepare_btc_4h_purchase, prepare_eth_4h_purchase, etc., leaving the agent to guess why it would pick this one over a per-asset variant.
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 second sentence implies the workflow ('the wallet-enabled agent signs and retries the returned HTTPS request'), which tells the agent this is a prepare-then-retry step rather than a completion. But there is no explicit when-to-use, when-not-to-use, or pointer to discover_4h_setups / the per-symbol siblings as alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the exact paid URL and wallet steps for the independent BTC 4H setup. No funds move until the wallet or user authorizes the x402 request.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is partly covered. The description adds real context beyond that: that the output is a paid URL plus wallet steps, and that no funds move until wallet/user authorization, which is critical behavior for an agent orchestrating a payment flow.
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 sentences with zero filler: purpose first, then the payment-safety guarantee. Every sentence earns its place and the key constraint is not buried.
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 zero-param, no-output-schema tool the description does enough: it names the return payload (paid URL + wallet steps) and the safety guarantee. It leaves the relationship to the generic and other-asset siblings, and any URL expiry/reuse behavior, unstated.
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 takes zero parameters, so there is no parameter semantics to document and the baseline is 4. The description correctly implies the BTC 4H variant is selected by tool name alone rather than by an argument.
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?
States a specific verb and resource: 'Return the exact paid URL and wallet steps' for the 'BTC 4H setup'. The asset qualifier implicitly separates it from sibling prepare_eth_4h_purchase / prepare_xrp_4h_purchase variants, though it never names them or the generic prepare_4h_setup_purchase it presumably specializes.
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 'No funds move until the wallet or user authorizes' clause implies this is a pre-purchase step in an x402 flow, which hints at ordering. However, it gives no explicit guidance on when to pick this vs. the generic prepare_4h_setup_purchase or when to call discover_4h_setups first.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the exact paid URL and wallet steps for the independent ETH 4H setup. No funds move until the wallet or user authorizes the x402 request.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes beyond the readOnlyHint annotation by stating that no funds move until the wallet or user authorizes the x402 request, which reassures the agent this is a non-mutating prep step. It stops short of describing the response shape or what the 'wallet steps' actually look like.
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 sentences, zero filler, with the deliverable (paid URL and wallet steps) front-loaded and the safety caveat second. Nothing could be removed without losing information.
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 zero params and no output schema, the description covers the essentials: what comes back and the fact that funding is deferred. A note on what the caller does with the returned URL (i.e., the follow-up step) would close the remaining gap.
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 takes no parameters, so there is nothing for the description to disambiguate; the baseline applies. No parameter confusion is possible given the empty, additionalProperties:false 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?
Specific verb (prepare/return) plus the exact artifacts (paid URL and wallet steps) and the resource (the independent ETH 4H setup). The asset-specific naming separates it from prepare_btc_4h_purchase and peers, though it never explains how it differs from the generic prepare_4h_setup_purchase.
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 statement of when to call this versus the sibling prepare_* tools or discover_4h_setups; the asset name implies the case but the agent must infer it. The only conditional sentence is about authorization of the x402 request, which is a behavior, not a selection rule.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the exact paid URL and wallet steps for the independent ONDO 4H setup. No funds move until the wallet or user authorizes the x402 request.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this materially by stating 'No funds move until the wallet or user authorizes the x402 request' — clarifying that this call is preparatory and that payment is a separate human/wallet-gated step. It stops short of explaining what the x402 authorization flow looks like or whether the returned URL expires.
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 short sentences, no filler. The deliverable (paid URL + wallet steps) is front-loaded and the safety caveat follows immediately.
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 zero params and no output schema, the description carries the burden of describing the return value, and it does name the two artifacts (paid URL, wallet steps). It could go further by indicating the response shape or the sequence of wallet actions, but for a simple zero-arg preparation tool this is close to sufficient.
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 takes zero parameters, so the baseline is 4. There is nothing for the description to disambiguate, and the single sentence correctly implies the call is invoked without inputs.
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?
States a specific verb and resource: 'Return the exact paid URL and wallet steps' for the 'independent ONDO 4H setup'. An agent can distinguish it from the BTC/ETH/XRP/TZ siblings by the named asset. However it never contrasts itself with the generic prepare_4h_setup_purchase sibling, so differentiation relies on the title's asset name rather than explicit routing.
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 when-to-use or when-not-to-use guidance. With six sibling 'prepare_*_purchase' tools, the description never says whether this is the ONDO-specific path, what 'independent' means versus the generic setup, or what prerequisite state is needed before calling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the exact paid URL and wallet steps for the independent TZ SELECT 4H setup. No funds move until the wallet or user authorizes the x402 request.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already mark the tool as read-only and closed-world, and the description adds important context: it returns a paid URL and wallet steps, and no funds move until the wallet or user authorizes the x402 request. That clarifies the safety gate beyond the annotations, though it does not describe edge cases 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?
Two compact sentences with the core output and the payment-authorization constraint front-loaded. There is no wasted 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?
For a zero-parameter preparation tool with no output schema, the description adequately explains what is returned (paid URL and wallet steps) and the crucial safety condition (no funds move without authorization). It could be slightly more complete if it clarified how this differs from the generic purchase-preparation sibling.
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 input parameters, so there is nothing for the description to disambiguate. The baseline for zero-parameter tools 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 gives a specific verb and resource: returning the exact paid URL and wallet steps for the TZ SELECT 4H setup. It clearly identifies the asset-specific scope, though it does not explicitly say how it differs from the generic prepare_4h_setup_purchase sibling.
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 this is the preparation step for a TZ SELECT 4H purchase and notes that funds only move after authorization. However, it gives no explicit guidance on when to use this tool versus discover_4h_setups or prepare_4h_setup_purchase.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the exact paid URL and wallet steps for the independent XRP 4H setup. No funds move until the wallet or user authorizes the x402 request.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this by clarifying that no funds move without wallet/user authorization of the x402 request — meaningful context about the two-step payment flow. It also indicates the return content (paid URL plus wallet steps), which is beyond what the annotations convey. It stops short of explaining what happens after authorization or any rate/expiry constraints.
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 short sentences, front-loaded with what is returned, followed by the safety caveat. Every sentence earns its place, though 'independent' is slightly vague and adds little actionable meaning.
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, no output schema, and simple read-only annotations, the description covers what the agent needs: what comes back (paid URL and wallet steps) and that nothing is charged automatically. Only a note on the expected follow-up call after authorization would make it fully 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?
The tool takes zero parameters, so the baseline is 4 per the rubric. The description correctly implies no input is required, and there are no parameters whose semantics need explaining.
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?
States a specific verb and resource: 'Return the exact paid URL and wallet steps for the independent XRP 4H setup.' The asset-specific scope is clear and matches the asset-per-sibling pattern (prepare_btc_4h_purchase, prepare_eth_4h_purchase, etc.). It does not explicitly contrast itself with the generic prepare_4h_setup_purchase, but the XRP scoping is 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?
'No funds move until the wallet or user authorizes the x402 request' implies this is a pre-authorization preparation step in a multi-step flow, which is useful implied usage. However, it never says when to pick this over prepare_4h_setup_purchase or the sibling asset tools, and no prerequisites or ordering guidance is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
discover_4h_setupsget_performance_evidenceprepare_4h_setup_purchaseprepare_btc_4h_purchaseprepare_eth_4h_purchaseprepare_ondo_4h_purchaseprepare_tz_select_4h_purchaseprepare_xrp_4h_purchaseCrypto market context, BSC alerts & token verdicts for agents. x402 on Base.
Crypto market intelligence for AI agents: sentiment, flow, Oracle readings. x402. NFA.
x402 market intel + $1 trade decisions: crypto, US & EU stocks, order flow, perps, macro, filings
Pay-per-call crypto signals, token verdicts, flows & briefs. x402 USDC on Base. Signal-only.
Add one secure layer between your agents and this server.
