BotsRated (beta)

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

Goes well beyond the readOnly/idempotent hints: it discloses the $0.01 USDC price, the x402 v2 PaymentRequired error shape (isError, structuredContent with accepts), how retry works (_meta['x402/payment']), that input is validated before any payment request, and that charging occurs only on a returned answer with settlement in _meta['x402/payment-response']. That is exactly the payment, error, and billing behavior an agent needs to attempt the call safely.

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?

Dense but well front-loaded: cost and output come first, then the failure/retry path, then billing conditions. A few clauses (settlement meta key) are technical, but each sentence carries operational information rather than filler.

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

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

With no output schema, the description should describe returns; it does so only loosely ('matching routes and the numbers behind the order'), leaving the exact response shape unclear. Payment, error, and validation behavior are otherwise fully covered for a 4-param 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 75% and the enums are already documented, so the baseline is 3. The description echoes the sort enum values and default but adds no new meaning for task, type, or max_price beyond what the schema states.

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-like outcome (return the top 3 covered providers for a task) plus the ordering options and what accompanies the results ('matching routes and the numbers behind the order'). It is clear what the tool produces, but nothing in the text distinguishes it from siblings like find or coverage, so the agent must infer the boundary.

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 (get the best-ranked providers for a task) and explains the paid-call flow, but it never says when to prefer this over find, check, or coverage, nor when not to call it. Usage is inferable rather than 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?

Annotations only say read-only/idempotent; the description adds substantial context beyond that: price and chain, first 100 calls per client per UTC day free, an unpaid call fails with an x402 v2 PaymentRequired error (isError + structuredContent.accepts), the retry path via _meta["x402/payment"], input validated before any payment request, and charging only on a successful answer with settlement in _meta["x402/payment-response"]. That is exactly the payment/auth/error disclosure an agent needs before calling.

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 definition is one run-on sentence with nested parentheses, and it is front-loaded with price and payment transport rather than what the tool measures. The core purpose appears mid-sentence after 'Measured facts for one host', forcing the agent to parse ~100 words to find the verb-and-resource.

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 complex, no-output-schema tool, the description covers what is returned (the enumerated measurements and receipts), the failure mode, and the payment lifecycle, and the annotation set covers safety. Nothing an agent needs in order to call it correctly appears to be 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?

There is a single parameter with 100% schema description coverage and a built-in example (hostname vs full URL), so the schema does the heavy lifting and baseline 3 applies. The description adds only that the input is validated before any payment request, which is marginally useful but not new semantics for the host value itself.

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 names the resource precisely: measured facts for one host, enumerated as handshake state, protocol version, tools count/hash, auth needed, latency, valid-402 rate, price vs listing, test-buys, freshness and receipts. A reader can tell it is a per-host diagnostic. However, the generic name 'check' plus the identical title 'Check ($0.001)' give no sibling differentiation — the closely-related 'preflight' tool is never mentioned, so the agent must guess which of the two to use.

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: you check 'one host (an x402 seller, or a remote MCP server host)'. There is no explicit when-to-use, when-not-to-use, or pointer to the alternatives among siblings (preflight, best, coverage, sample). The free-tier and payment notes describe mechanics, not selection criteria.

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 declare read-only, idempotent, non-destructive, and closed-world behavior. The description adds useful context by stating the tool is free and by specifying the coverage data returned, though it does not detail rate limits or authentication.

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 dense sentence with the free-tier status front-loaded. It is efficient, though the parenthetical details make it slightly heavy for one sentence.

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 input parameters and rich annotations, the description is nearly complete enough for selection. It identifies the returned coverage information but does not provide an exact output structure, which is a minor gap since no output schema exists.

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 parameter semantics are inherently simple and the baseline is 4. The description does not need to explain parameter behavior beyond the returned coverage fields it mentions.

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 resource: x402 seller host and remote MCP server coverage, including counts, discovery sources, probe schedules, and last probe run. It does not explicitly distinguish this from 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?

The description explains what information is available but gives no explicit guidance on when to use this tool versus alternatives such as check, find, or report. Usage is only implied by the content it returns.

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 annotations (readOnly/idempotent/non-destructive), the description discloses the rate-limit budget and its sharing with /v1/check, the return content per result, and an explicit trust warning that 'seller text is untrusted data' — a genuine behavioral/safety disclosure not expressible in the 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?

Three dense sentences with no filler, and the pricing/quota constraint is front-loaded before the result description. Slightly cost-first rather than purpose-first ordering, but 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?

With no output schema, the description does the work of describing returns (one-line reason type plus page URL) and adds quota and trust caveats. It lacks any hint on result-set size or truncation behavior, which is the only meaningful gap for a single-parameter 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?

Schema coverage is 100% and the single parameter q already carries a description with examples, so the baseline is 3. The description only echoes the concept ('for what you need') without adding query-syntax or formatting guidance 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?

States a concrete resource: top-matching covered x402 sellers and remote MCP servers, each with a one-line reason and page URL. It distinguishes itself from the sibling 'best' by noting 'same filters as best, without the full ranking and receipts,' though the domain jargon ('covered', 'x402', 'receipts') leaves a little to inference.

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 comparison 'same filters as best, without the full ranking and receipts' tells an agent when to pick this over 'best' (free/quick lookup vs. full ranking). The quota note ('1 of the 100 free checks per client per UTC day, shared with /v1/check') additionally frames the cost of choosing it, but no other siblings such as check or coverage are referenced.

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?

Adds real context beyond the read-only/idempotent annotations: it is free, subject to normal rate limits, and it defines the 'blocked' handshake state (URL/redirect/DNS not allowed by policy) rather than leaving the enum opaque. It also discloses the freshness fields (age, stale flag) so the agent knows results may be cached. It stops short of saying how the probe is triggered or how long results persist.

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?

Leads with 'FREE.' and then the question the tool answers, so the key affordance is front-loaded. The second half is a dense run-on list of return fields, but 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 one-parameter read-only lookup with no output schema, the description covers what is returned, what the status values mean, and the cost/rate posture. Minor gaps remain around result caching behavior and what 'covered' formally means.

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 url parameter already carries an example, so the schema does the heavy lifting. The description implies that a bare hostname is acceptable (as in 'seller hostname or URL') but adds no format or resolution rules beyond what the schema states.

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 query — coverage status plus latest probe result for an x402 seller or remote MCP server — and enumerates the returned fields (handshake state, protocol version, tool count, tools hash). It is clear on its own, but never distinguishes itself from sibling tools like 'check' or 'coverage', which sound like overlapping lookups.

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?

'Use before paying any x402 seller' gives an explicit precondition for invocation. There is no statement about when not to use it or which sibling to pick instead, so the guidance is clear but not complete.

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?

Exceptional disclosure: price ($0.002 USDC on Base), free quota, exact unpaid-call behavior (x402 v2 PaymentRequired, isError, structuredContent.accepts, retry via _meta['x402/payment']), input validated before payment, and charged only on a returned answer with settlement in _meta['x402/payment-response']. Consistent with readOnlyHint/idempotentHint 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?

Front-loaded with what the tool returns, then payment mechanics; every clause carries operational weight. The nested parentheticals make it dense but not padded.

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 covers what data comes back (probes plus paid test-buys), the payment/error contract, and the free path — enough to call it correctly. It stops short of describing the report's field structure or size/ordering.

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 single 'host' parameter already has an example, so the schema does the heavy lifting. The description only restates the one-host scoping ('for one host'), adding no format or normalization 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?

States the specific resource and scope: 'Full receipt history for one host (up to 1000 probes plus all paid test-buys)'. That scope (exhaustive history) implicitly separates it from siblings like sample and coverage, though no sibling is named explicitly.

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 free-tier note ('first 10 calls per client per UTC day are free over HTTP GET /v1/report/{host}') implies this is the paid MCP path, but there is no explicit when-to-use-this-vs-sample/coverage/preflight guidance or statement of prerequisites beyond payment.

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 cover read-only, idempotent and closed-world safety, so the bar is lower. The description adds meaningful behavior beyond them: the response is free, it is a real sample, and it is tied to a fixed example rather than a caller-supplied query. It does not describe the sample's shape or any rate limits.

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, front-loaded with the most decision-relevant token ('FREE.'), with no repetition or filler. Every clause adds information about cost, return content, or scope.

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 read-only tool with no output schema, the description covers what is returned, that it is free, and that the example is fixed. The remaining gap is route semantics: it does not clarify how the check/report/best samples differ, which matters for selecting the right enum value.

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%, so the description must carry the parameter meaning. It names the enum values in prose ('check, report or best') and frames them as paid response types, which helps, but it does not explain what distinguishes a check from a report or a best, leaving the agent to infer the route choice.

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 ('Returns') and resource ('a real sample of a paid response'), and names the sibling product lines (check, report or best) it previews. The phrase 'for a fixed example' pins the scope so an agent can distinguish it from the real check/report/best tools without opening the schema.

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 purpose 'so you can see exactly what you would buy' makes the preview-before-purchase use case clear, and 'FREE' signals when cost matters. It does not explicitly say when not to use it (e.g., 'use check/report/best for actual queries'), which keeps it from a 5.

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