Vortex

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

With no annotations provided, the description is the sole source of behavioral disclosure. It states the tool returns a manifest, is free, and lists the manifest's contents, implying a read-only scope with no side effects. It doesn't specify the exact output format or potential size limits, but for a discovery tool with zero parameters, this is adequate and does not contradict any annotations (since there are none).

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 paragraphs with the core action front-loaded, followed by a clear 'When to use' line and a cost note. Every sentence earns its place: purpose, usage guidance, and cost. No redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (no parameters, no output schema), the description fully covers what it does, what the manifest includes, when to use it, and that it's free. The 'machine-readable manifest' phrasing hints at the output format, and the enumerated contents compensate for the absence of an output schema. Nothing an agent needs to call it correctly is missing.

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 description appropriately adds no parameter information. The empty schema already indicates this, and the description doesn't need to explain missing fields. The baseline of 4 for zero parameters is justified because the description complements the schema without redundancy.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Return') and a precise resource ('the full machine-readable manifest of Vortex'), enumerating exactly what the manifest contains (operations, prices, input schemas, payment). This clearly distinguishes it from sibling tools, which are individual operations like credit_deposit or find, by positioning it as the whole-API discovery 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?

It explicitly provides a usage condition: 'Call this first if you have never used Vortex and want to know what it can do and what it costs.' This gives clear when-to-use context, and the sibling tools are the alternatives one would use after this discovery call, so the guidance is effectively unambiguous.

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 goes beyond the readOnlyHint=false annotation by explaining the settlement model: 'One on-chain settlement, then every call is debited off-chain.' It also clarifies that the tool is free despite being a purchase. It stops short of mentioning potential requirements or outcomes like wallet approval or the returned transaction status.

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 compact and front-loaded: action, usage trigger, and price are each given in a distinct sentence or short section. Every sentence earns its place, and there is no repetition of schema or title 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 one-parameter top-up tool, the description covers the purpose, when to use it, the on-chain settlement model, and the cost implications. It does not describe the response format (e.g., confirmation or new balance), but given the simple, low-complexity action and lack of an output schema, this is a minor 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 schema fully documents amount_usd with description 'One of 1, 5 or 20. Defaults to 1.', and coverage is 100%. The description adds no parameter-level detail, but with this high schema coverage 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 opens with 'Buy Vortex credit with USDC on Base over x402' — a specific verb, resource, and payment rail. The title 'Top up balance' is consistent, and no sibling tool appears to be a credit/payment tool, so there is no ambiguity about what this tool does.

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 explicitly says 'When to use: Call when your balance is low.' It also adds economic context by noting that operations cost fractions of a cent, so a single deposit covers many calls. This gives the agent a clear condition for selecting this tool.

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

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

Annotations mark this as read-only and closed-world, and the description adds substantial behavioral context: it returns one of three verdicts (reaches, cannot_reach, unknown) rather than raw data, and lists the kinds of evidence involved. This goes well beyond what annotations alone convey.

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 organized into a clear intro, an explicit usage section, and a price line. It is slightly longer than necessary and some phrasing is redundant ('not just data' with 'verdict'), but every section earns its place and key information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter read-only tool with no output schema, the description is effectively complete: it explains when to call, what data is considered, what verdict values will be returned, and the cost. An agent can decide to invoke or avoid this tool without needing more 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 schema already fully documents both parameters with examples and a pattern, so the description does not need to add much. The description loosely refers to 'storefront' and 'destination,' matching the store and destination fields, but adds no parameter-level meaning 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's function: determining whether one storefront can serve one destination and returning a verdict. It enumerates concrete inputs (shipping zones, currency, cards, buyer reports, reach changes), which makes the tool's purpose distinguishable from vague sibling names like find, watch, or capabilities.

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 an explicit trigger: call when a store is already in mind and about to spend real money. It does not name specific siblings as alternatives or explicitly state when not to use it, but the usage context is clear enough to guide selection.

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

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

Annotations already mark readOnlyHint=true, and the description adds consistent behavioral context: live price/stock and delivery-reach filtering. It also discloses the per-call price. There is no contradiction with the annotations, and no hidden mutation or side effect is suggested.

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 core behavior is front-loaded in the first sentence, followed by a sharp when-to-use rationale and cost. There is no filler, no restatement of parameter names, and every sentence contributes to correct tool selection and invocation.

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 read-only search tool with 100% schema coverage, the description covers what the result contains (reachable storefronts with live price and stock), when to call it, and its cost. It could specify the return shape in more detail since there is no output schema, but nothing essential for invoking it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3: the schema already documents need, destination, limit, in_stock_only, and max_price_usd. The tool description only restates the destination/reach concept without adding meaningful detail 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 opens with a specific verb and resource: 'Search real storefronts for a product' and immediately clarifies the tool's differentiator—returning only items that can ship to the destination. This clearly distinguishes it from generic product indexes and gives an agent a precise mental model.

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 explicit when-to-use guidance: 'Call this before shopping anywhere else' and explains why, citing country-specific storefronts and late-stage checkout failures. It does not name concrete sibling tools or provide when-not-to-use conditions, so it stops short of a 5.

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

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

Annotations already mark it read-only and closed-world; the description adds meaningful behavioral detail: how many observations Vortex has, that the percentile is withheld when the series is too short, and that stock-out and shipping changes are covered. No output schema or pagination specifics are provided, but the read-only annotation lowers the bar.

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, front-loaded with the main behavior, and every sentence earns its place: what it returns, when to call it, an edge-case behavior, and price. The phrasing is slightly awkward but structurally 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?

For a two-parameter read-only tool with complete schema coverage, the description conveys the decision context, the key return categories, and an important edge case. It doesn't spell out exact output shapes, but no output schema exists and the stated information is enough to use it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3 even without additional parameter detail. The description mentions 'product' and 'series' but adds no semantic meaning beyond the schema's product URL and days 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 identifies the tool as returning historical price, stock, and shipping data for a product, including where today's price sits against its own record. It lacks an explicit verb phrase and does not name or differentiate sibling tools, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"When to use: Call this when you have a candidate and want to know whether to buy now or wait" is explicit about the intended situation. It does not provide when-not-to-use guidance or name alternatives such as watch or report, 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?

With no annotations, the description carries the full behavioral burden. It discloses that the tool is free, grants a trial credit, requires no signup, and returns a token needed for all subsequent calls. It could go further by stating what happens if called again or how the identity is persisted, but the key behavioral traits are present.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded, with the core purpose and critical usage instruction appearing early. Minor redundancy exists between 'Free' in the first sentence and the later 'Price: Free.' line, but overall every section earns its place and the format is easy to scan.

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 provides enough context for an agent to call this tool correctly: when to call it, why it must be first, what it returns, and what it costs. Since there is no output schema, a slightly more explicit description of the response shape would improve completeness, but the token requirement is stated clearly enough for practical use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all four parameters in detail. The description reinforces that the wallet is the permanent identity and mentions the returned token, but it does not add meaningful parameter-level meaning beyond the schema. A baseline of 3 is appropriate given the high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Turn a wallet address into a permanent Vortex identity and an API token.' This clearly distinguishes the tool from siblings like whoami or credit_deposit, which serve different purposes. The outcome is concrete and immediately understandable.

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?

Explicit usage guidance is provided: 'Call this once, before anything else. You need the returned token for every other call.' This tells the agent exactly when to invoke the tool and why it must be called first. No ambiguity remains about sequencing or dependency.

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

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

Annotations already mark the tool as read-only, and the description adds useful behavioral context beyond that: 'If Vortex has no rule on file for the destination it says so instead of returning a confident guess.' The example also sets expectations about real-world totals. No contradiction with annotations.

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 efficient and well-structured, front-loading the core behavior, then providing a concrete example, then a 'When to use' section. The price line is relevant for cost-aware selection. Nothing is verbose, though the example plus pricing could be seen as slightly more than strictly necessary.

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 there is no output schema, the description does a good job explaining what the result contains: itemized cost components and the name and effective date of the tax rule. It also covers the no-rule fallback. It does not deeply describe all input combinations, but the schema already covers those, so the description is reasonably complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents destination, product, item_usd, and shipping_usd. The description's example with a US$120 item into Brazil adds context but does not materially improve parameter semantics beyond what the schema provides. Baseline 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's function through its output specification: item plus shipping, import tax, and local tax itemized for a destination, plus the tax rule applied. The example and 'shelf price is not the number to budget against' reinforce the landed-cost purpose. It does not explicitly name or differentiate among sibling tools, so it falls just short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit guidance: 'Call this before committing to a cross-border purchase, and before comparing two stores in different countries.' This provides clear context for when to use the tool. It does not mention alternative sibling tools or exclusions, which prevents 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?

Beyond the sparse annotations, the description discloses that reports are free, verified against the merchant's own feed before counting, and that contradicted claims are stored and marked as contradicted rather than believed. This is useful behavioral context. It does not address rate limits or edit/delete behavior, but the core trust model is transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose, behavior, and usage are each clearly present and the description is front-loaded with what the tool does. However, 'Free' appears twice and the final 'Price: Free' line repeats the first sentence, adding redundancy without new information. 'Makes every later answer better' is also somewhat vague.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the schema covers all five parameters and the description covers when to call, what happens to reports, and the unique value of the freight field, this is sufficiently complete for correct invocation. There is no output schema, but return values are not necessary to decide when or how to call this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds extra meaning for shipping_usd by calling it 'the one number Vortex cannot collect for itself,' and it frames outcome as covering both good and bad attempts. The product URL requirement is already in the schema, so the description contributes a modest but real increment above baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific action and object: 'Tell Vortex how a purchase actually went.' This clearly identifies the tool's purpose and naturally distinguishes it from read-oriented siblings like find, history, and landed. It also adds meaningful context about merchant-feed verification and contradiction handling.

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 an explicit trigger condition: 'Call this after any purchase attempt, good or bad.' It also notes that freight quotes are the one number Vortex cannot collect itself, giving a clear reason to use this tool. It does not explicitly mention alternatives or exclusions, but the tool's role is unique among the visible 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?

Annotations only say readOnlyHint=false and openWorldHint=false, so the description adds meaningful behavioral context: registering a standing interest, catching changes at the moment they happen, optional callback via POST, and the per-call price. It could go further by disclosing watch lifecycle or cancellation behavior, but the core side effects are clear.

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 compact and front-loaded: purpose, usage guidance, then cost. Every sentence earns its place and none are redundant with the schema.

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 six parameters, a fully descriptive schema, and no output schema, the description covers the essential context: purpose, when to use it, how the tool behaves, and cost. The main gaps are lifecycle details (whether/canceling a watch) and what the registration call returns, but these are not required to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all six parameters and their requirements. The description's prose restates the high-level event types (price drop, back in stock, store reach change) but does not add parameter semantics beyond what the schema already provides.

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 opens with a specific verb and resource: 'Register standing interest in a product or a store,' and enumerates the event types (price drop, back in stock, reach change). It also explicitly distinguishes itself from the sibling tool find by saying to call it instead of polling find on a schedule.

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 has a dedicated 'When to use' section that names the alternative (find), states the condition for this tool ('instead of polling find on a schedule'), and gives a concrete reason (cost and immediacy). This is explicit 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?

The annotation readOnlyHint=true already covers the safety profile, and the description adds the cost detail ('Free') and the fact that it returns account-related data. It does not add much behavioral context beyond what annotations provide, such as authentication requirements or response format details. The description is not misleading and is consistent with the read-only annotation.

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, with the core result ('Your handle, wallet, balance and usage') stated first. The 'Free' information is repeated twice, once in the opening and again as 'Price: Free,' which is slightly redundant but not harmful. Overall it is efficient and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, read-only identity/balance tool, the description provides enough context: what data is returned, when to use it, and that it is free. There is no output schema, but the listed fields ('handle, wallet, balance and usage') give a reasonable expectation of the response. No critical information appears missing for an agent to invoke it correctly.

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 there is nothing for the schema or description to document. Schema coverage is trivially 100%, and the description's mention of 'wallet, balance and usage' gives the agent a sense of what data will be relevant. This fully satisfies the baseline 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?

The description clearly identifies the tool as returning the caller's handle, wallet, balance, and usage, which is specific enough to understand its purpose. It lacks an explicit verb like 'retrieves' or 'returns,' but the title 'Who am I' plus the listed data makes the function clear. It does not explicitly differentiate from siblings, though its identity/account scope is distinct from tools like credit_deposit or identity_create.

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 explicit when-to-use scenarios: 'check your balance before a run' and 'confirm your token still works.' This provides clear practical context for an agent deciding to invoke it. It does not mention alternatives or when not to use it, but for a trivial identity/balance check the use cases are sufficient.

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