switch402

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

With no annotations, the description carries the burden and does well: it discloses deduplication, default and max limit values, exact price ($0.001 USDC on Base via x402), that charges occur only on success, and the failure/payment-requirement behavior. What it omits is whether the page is fetched once (no recursion) and any rate-limit or auth context 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?

Two dense sentences with the output behavior front-loaded and pricing/retry mechanics trailing; no filler or restatement of the tool name.

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 tool with no output schema, the description covers what is returned, the cap semantics, and the entire paid-call lifecycle. The only gap is the shape of the result (list of absolute URLs vs. relative) and confirmation that no recursion occurs.

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 50% (only url is documented), but the description compensates by explaining that limit is a dedupe cap with default 200 and max 1000, and that url refers to a page or site root whose links and sitemap are harvested. It adds real 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 states a concrete resource and scope: same-site URLs on the page plus sitemap URLs from robots.txt or /sitemap.xml, deduped and capped. That is specific enough to distinguish it from a full page-content fetcher like scrape, though it never names the siblings 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?

It clearly explains the payment retry protocol (unpaid calls return x402 requirements, retry with _meta["x402/payment"]), which is actionable usage guidance. However, it gives no guidance on when to choose map over scrape or scrape_lite, which is the main selection decision an agent faces.

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 and does well on the critical detail: it discloses that the call is paid via x402, charged only on success, and that unpaid calls return payment requirements requiring a retry with _meta["x402/payment"]. It does not describe rate limits or other failure modes, but the payment behavior is unusually well covered.

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 front-loaded with the returned fields and follows with necessary payment mechanics. Every sentence carries useful information, with no repetition 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?

There is no output schema, but the description lists the metadata categories an agent will receive and explains payment/retry behavior. It is largely complete for a one-parameter extraction tool, though it could say more about return structure and sibling differentiation.

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% and the single url parameter is already documented as a public http(s) HTML page. The description does not add syntax or format details beyond the schema, so the 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 enumerates the exact metadata fields returned (title, meta description, canonical, lang, OpenGraph/Twitter tags, JSON-LD), so the resource and output scope are clear. It does not explicitly distinguish this from the scrape or scrape_lite siblings, which keeps it from 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?

It gives invocation guidance around payment and retry behavior, but does not state when to choose this tool over scrape, scrape_lite, or map. Usage is implied by the metadata-specific output list rather than explicitly contrasted with alternatives.

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 and does so well: it discloses pricing, x402 payment flow, that charges apply only on successful text extraction, how unpaid calls behave, and the retry mechanism. It also states page/size limits and the text-based PDF constraint.

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: input/output behavior first, then limits, then payment details. Every clause adds useful information for invoking the tool correctly.

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?

There is no output schema, so the description must convey return behavior; 'text page by page out' and 'charged only when text comes back' do this adequately. It could be slightly more explicit about the exact return shape and behavior on scanned/non-text PDFs.

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 both url and pages thoroughly. The description adds the 50-page/10 MB constraints but little else about parameter semantics beyond what the schema 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 clearly states a PDF URL is converted into page-by-page text, which is a specific resource + transformation. It does not explicitly differentiate itself from siblings such as scrape or metadata, so it falls 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?

It gives clear usage context: public http(s) PDF URLs, text-based PDFs only, and page/size limits. It does not explicitly name alternatives like scrape or metadata or state when those should be 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?

With no annotations, the description carries the full behavioral burden. It discloses that the tool is 'Free' and lists several outputs, but omits permissions, side effects, network behavior, data freshness, and what happens when providers are unhealthy or payment status is unavailable.

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, front-loaded sentence with no filler. It is appropriately terse for a simple two-parameter tool, though the phrase 'Our price' is slightly ambiguous.

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 annotations, no output schema, and a misleading url schema description, the description is not complete enough to call the tool confidently. It lists some outputs but leaves the core relationship between the url input and the quote result undefined.

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 50%, and the description only implicitly references the 'tier' parameter via 'price for a tier' without explaining the url parameter at all. Worse, the schema's url description says 'convert to markdown,' which conflicts with the quote purpose, and the description does nothing to clarify the actual role of url.

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 lists return data (price for a tier, healthy provider count, latency, payment status) but does not state a clear action verb or explain what the tool does with the required URL. The title 'Price and availability' helps, but without the title the purpose is vague and it never differentiates itself from the sibling scrape tools.

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 scrape or scrape_lite, nor any when-not-to-use conditions. The description merely lists outputs and leaves the agent to infer the tool's role.

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 and does well: it discloses automatic provider failover, the exact price ($0.008 USDC on Base), that charging happens only on success, and the failure contract for unpaid calls including the retry key. It omits timeout/rate-limit behaviour and any note on JS-rendered or blocked pages, which keeps it from a 5.

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 short sentences, front-loaded with what the tool does, then cost, then the retry contract. Every sentence carries operational information and none is 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 one-parameter, no-output-schema tool the description covers the essentials an agent needs before calling: the output form (clean markdown), the reliability model (failover), and the payment protocol end to end. What is missing is edge-case behaviour (timeouts, empty/JS-only pages, truncation of very large pages).

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 there is only one parameter, whose schema description already says 'Public http(s) page to convert to markdown.' The description adds no extra constraint on the url (e.g. auth-gated pages, redirects, size limits), so it sits at the baseline rather than compensating.

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 and resource ('Page to clean markdown') plus the routing behaviour ('healthy provider with automatic failover'), which is more than a restated title. It never mentions the sibling tools scrape_lite or quote, so an agent cannot tell from the text why it should pick this paid variant over the lite one.

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 guidance is limited to the payment handshake: unpaid calls return x402 requirements and should be retried with _meta["x402/payment"]. That is genuinely actionable for the calling flow, but there is no guidance on when to prefer this over scrape_lite or quote, which is the main selection decision an agent faces.

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 and does well: it discloses per-page cost, the payment rail (USDC on Base via x402), that billing occurs only on success, and exactly what an unpaid call returns plus how to continue. It leaves 'failover' undefined and says nothing about timeouts or dynamic-page limitations.

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 purpose is front-loaded in the first clause and the payment mechanics follow tightly. Minor redundancy in quoting '$0.003 per page' twice, and 'with failover' is a dangling phrase that costs a clause without conveying behavior.

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?

No output schema and no annotations, yet the description covers the essentials an agent needs: the markdown return type, price, payment flow, and the retry path. The main gap is the unexplained 'failover' claim and no note on behavior for pages that fail or require rendering.

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 only one parameter and schema description coverage is 100%, so the schema already explains `url` fully. The description's 'any public page' is consistent with but does not meaningfully extend the schema's 'Public http(s) page', so the baseline 3 applies.

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

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

States a specific verb and resource: convert a URL to clean markdown, scoped to the 'lite' endpoint. It is clear what the tool does, but it never differentiates itself from the sibling `scrape` (the obvious full/heavier variant) beyond the word 'failover', leaving the agent to infer lite vs. full.

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?

Implicitly defines usage ('any public page', the cheaper lite path) and gives a concrete recovery procedure for the unpaid case: retry with _meta["x402/payment"]. However, it never says when to pick this over `scrape`, `search`, or `map`, so routing between siblings is left to inference.

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 and does so: cost ($0.008 USDC), charge-only-on-success semantics, the unpaid failure path (x402 payment requirements returned), and the exact retry channel (_meta["x402/payment"]). It also discloses rendering behavior (JS rendered) and viewport size.

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 compact sentences, each earning its place: what is captured, what it costs and returns, and how to recover from the payment failure. Front-loaded with the capability before price details.

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?

No output schema exists, yet the description names the return field and encoding, covers payment lifecycle and failure recovery, and specifies the rendering context. Only gaps are timing/timeout behavior and an explicit contrast with screenshot_full.

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?

Single parameter with 100% schema coverage means the schema already defines 'url'; the description adds the constraint that it must be a public http(s) page and names the result field image_base64, which the schema 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?

States a specific verb+resource ('Screenshot ... of a public page'), plus the defining scope ('visible part', '1280x800 viewport', 'JavaScript rendered') that tells it apart from screenshot_full and scrape without opening a 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 qualifier 'visible part' implicitly signals the viewport-only case versus a full-page sibling, and 'public page' excludes authenticated content, but screenshot_full is never named so the agent must infer the routing rule. No explicit when-not 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, the description carries the full burden and does so well: it discloses JavaScript rendering, the exact output field image_base64, the $0.012 USDC cost on Base via x402, that billing occurs only on success, and how unpaid calls behave with retry via _meta["x402/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 compact sentences that front-load the capture result and then cover the payment behavior. Every clause earns its place by conveying output location, rendering behavior, cost, and failure/retry semantics.

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

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

Despite having no output schema, the description identifies the return field image_base64 and explains the x402 payment success/failure flow. That is enough for an agent to call the tool and handle the paid-call protocol 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 coverage is 100% and the single url parameter is already documented as a public http(s) page. The description adds context about JavaScript rendering and full-page scope but no additional syntax or constraints for the parameter itself, so baseline 3 applies.

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

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

The description states a specific resource and output: the whole scrollable page captured as a base64 PNG in image_base64. The 'whole scrollable page' phrasing implicitly distinguishes it from the sibling screenshot tool, though it does not name that sibling 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?

It gives clear context for when this tool is appropriate: full-page capture of a JavaScript-rendered page. It does not explicitly name the alternative viewport screenshot tool or provide exclusions, so it falls short of a 5.

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

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

With no annotations, the description carries the full behavioral burden and does well: it discloses the cost, that charges occur only on success, and how unpaid calls return x402 requirements with a retry path. It does not cover rate limits or explicitly state read-only safety, but the essential payment behavior is clearly explained.

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 three efficient sentences with no wasted language. Output shape and payment flow are front-loaded and immediately useful.

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 search tool with no output schema, the description is nearly complete: it explains return fields, result limit, pricing, and retry behavior. The main gap is the lack of explicit sibling-tool selection guidance, but an agent has enough 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 both parameters are already documented in the schema. The description adds the maximum result count and output fields but does not add syntax or format detail beyond what the schema provides, 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 states a specific verb and resource: query in, ranked web results out, with title, URL, and snippet. It distinguishes itself from siblings like scrape and map by describing search-result behavior, but it does not explicitly contrast itself with those alternatives.

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

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

The description implies usage for web search but does not say when to use this tool versus scrape, map, metadata, or quote. It does give a clear payment retry condition, which is useful context but is behavioral rather than selection guidance.

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