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

It goes beyond standard metadata by disclosing crucial operational details like 'Costs no credit,' the specific failure code (HTTP 402), and the link to upgrade plans, adding significant behavioral context.

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

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

While slightly verbose, every part of the paragraph is high-value operational instruction. The critical information (what it does and when to use it) is front-loaded effectively.

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 lack of an output schema, the description provides a complete narrative of the account data, including renewal cycles and failure modes, leaving no critical data gaps.

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?

Since there are zero parameters, the baseline score is 4. The description effectively explains the scope of the data return, which is the only thing an agent needs to know about the 'input' operation.

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 specifies the data retrieved (plan, used, remaining, reset time, and upgrade page) for the ScrapingBot account, distinguishing it from general data scraping siblings.

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 provides explicit guidance on when to use the tool—'Check it before a series of scrapes'—and provides a clear operational trigger for invocation: low credit alerts or HTTP 402 failure.

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 cover read-only and open-world status, but the description adds two traits they cannot express: it blocks for roughly a minute and consumes no credit. That latency and cost disclosure is genuinely useful for an agent deciding whether to call it inline, though the still-pending failure mode is left unstated.

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 action and resource, with the two behavioral facts appended compactly. No 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, so the description could say more about what the returned result looks like or how to handle a still-pending response; however, for a simple 2-parameter retrieval companion to scrape_social_media it covers everything needed 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 0%, so the description has to carry the load; it names both parameters and tells the agent where responseId comes from ('from its scraper and responseId'), but does not state that scraper must match the scraper used in the original pending request or explain the enum values.

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 ('Get the result of a scrape_social_media request') and explicitly ties it to the sibling tool that produces the pending request, so an agent can tell it apart from the scrape_* family 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?

Clearly conditions use on a prior scrape_social_media call that returned 'still pending', and names that sibling as the originating alternative. It stops short of saying what to do if the result is still not ready after the wait (retry vs. give up), which is the one remaining routing decision.

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 readOnlyHint=true and openWorldHint=false, and the description adds genuinely new operational context: the call "costs no credit," which matters on a metered scraping service. It also discloses the shape of the diagnostic data (per-day credits, failure errors), though it says nothing about latency or data freshness.

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 front-loaded sentences: what it returns, why to use it, and its cost. The enumerated metric list is long but every item is informative since there is no output schema. Minor redundancy between "latest requests" and the earlier metric list.

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 carries the burden of describing return values, and it does so concretely, down to the fields of each recent-request entry (URL, API, success, credits, error). Combined with the fully documented schema, an agent has everything needed to call and interpret it.

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% — both `days` (1–90, default 30) and `recent` (0–50, default 10) are fully documented with ranges and defaults. The description mentions "over the last days" and "latest requests" but adds no syntax or usage nuance beyond the schema, 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 — retrieving ScrapingBot account usage over the last days — and enumerates the returned metrics (credits per day, requests per API, success rate, latest requests). This clearly separates it from the scrape_* siblings, which perform scraping rather than reporting account telemetry.

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?

"Useful to explain what used the credits or why requests fail" gives explicit diagnostic contexts for calling it. It does not name a sibling alternative (e.g. get_account), but the use case is unambiguous and no exclusions are needed for a read-only reporting 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?

Beyond the readOnly/openWorld annotations, it discloses credit costs, cost modifiers for useChrome and premiumProxy, refund behavior, protected-site billing, and automatic premium-proxy retry semantics. These are material operational details an agent could not infer from the schema.

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

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

The purpose and supported sites are front-loaded, followed by URL date guidance, return format, and billing behavior. It is dense but every major clause is useful, though the long list of protected-site examples could be tightened.

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 scraping tool with no output schema, the description explains the JSON return and some fields, plus billing and retry behavior. Search-result return shape and pagination are not covered, leaving a small completeness 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?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning by mapping useChrome and premiumProxy to specific credit costs and explaining premiumFallback billing. It does not add much for proxyCountry, but that parameter is already documented.

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

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

The description gives a precise verb ('Extract') and resource ('hotel or rental page... or a search results page') and names the exact travel sites covered. This clearly separates it from the retail, grocery, social, and real-estate siblings by domain.

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 provides clear usage context by naming supported travel sites and instructing users to put stay dates in the URL. It does not explicitly compare against alternatives such as scrape_raw_html or scrape_real_estate, but the domain context is strong.

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?

This description excels in behavioral transparency by disclosing crucial details beyond the annotations, including the tiered cost structure (1, 5, 10, 25 credits), specific site triggers for high cost, and the complex retry/refund logic. This information is essential for financial and operational planning.

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

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

The description is extremely dense and lengthy due to the high volume of operational, financial, and complex behavioral information it must convey. While it is efficient in its density, it sacrifices conciseness.

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

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

The definition is highly complete for a complex, high-risk tool. It covers the target data, the costs, the failures (refund policy), the success criteria for retries, and specific geographical exceptions, providing the agent with everything it needs to execute the tool safely and effectively.

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?

Since schema coverage is 100%, the baseline is 3. However, the description adds significant semantic value by explaining the *consequences* and *intent* of parameters like 'premiumProxy' and 'proxyCountry'—that they are required for circumventing site blocks and involve specific cost tiers.

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 tool is clearly defined as scraping grocery products, specifying the data extracted (title, price, image, brand, etc.). The name and title are highly specific and immediately distinguish it from the other scraping tools in the sibling list (e.g., real_estate, booking).

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 extensive functional context regarding when and why certain features are necessary (e.g., using premium proxies for blocked sites, using Chrome for JavaScript rendering). While it doesn't explicitly say 'Use this over X,' the functional constraints serve as excellent usage guidelines.

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?

Goes well beyond the readOnly/openWorld annotations by disclosing the credit cost model for each option, refunds on failure, the list of sites that force a premium proxy, and the automatic retry-with-premium-fallback behavior. It does not describe the response shape, but the cost and retry disclosures are exactly the kind of context the annotations cannot carry.

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-loads purpose and alternates, then the cost model. Dense but every sentence carries routing or billing information; the long single paragraph buries the pricing detail a bit and could be split, but there is no 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 7-parameter, no-output-schema tool, it covers routing, cost, retry semantics, and the special-domain case. The only real gap is that it doesn't describe the return payload (truncation via maxChars is only implied by the schema), but that is minor given the schema's completeness.

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 real meaning by tying useChrome and premiumProxy to concrete cost deltas and flagging which domains trigger premium pricing automatically. The premiumFallback behavior is restated with the billing condition, which reinforces rather than duplicates 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 specific verb and resource ('Fetch the HTML source of any public web page') plus the mechanism (ScrapingBot's proxies). It also distinguishes itself from every relevant sibling by name, so an agent can route correctly without opening other schemas.

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?

Explicitly says to prefer dedicated tools and enumerates which ones for which domains (retail, real estate, booking, search engine, social media), and notes social media is blocked here. Clear when-to-use and when-not-to-use.

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 far beyond annotations by detailing complex behaviors: pricing schemes, refund policies for failed requests, and the specific billing outcome of the retry mechanism for blocked sites. This operational knowledge is critical.

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?

While the description is detailed and lengthy, it is highly dense with value. It avoids fluff, with every sentence providing necessary operational constraints, such as cost or technical limitations.

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 complexity of the tool (multiple optional parameters, pricing structure, and varied site requirements), the description is complete, providing all necessary behavioral and cost contexts required for safe and effective tool invocation.

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

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

Although schema coverage is 100%, the description adds necessary semantic depth by explaining how certain parameters like `premiumProxy` and `premiumFallback` interact with site policies, retry success, and billing outcomes.

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 is explicit, stating it extracts data like price, surface, rooms, and location specifically from real estate sites (SeLoger, Zillow). It clearly defines the tool's resource and core function.

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 defines operational boundaries by mentioning specific supported sites (SeLoger, Rightmove) and warns that certain sites necessitate premium proxies, guiding the agent on when specific configurations are required.

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?

Goes far beyond the readOnlyHint/openWorldHint annotations: discloses credit pricing per option combination (1/5/10/25), refunds on failure, a named list of sites that force a premium proxy at 10 credits, and an automatic single retry on block with conditional billing that the result reports. These are exactly the cost and side-effect facts an agent needs before spending credits.

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 is front-loaded in the first sentence, followed by the cost/retry behavior, which is the right order. The middle section is dense with nested parentheticals (cost tiers, site lists) that take a second read, slightly reducing scannability, but no sentence is redundant.

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 still names the returned fields and the return format ('Returns JSON'), and it covers cost, refund, retry and protected-site behavior. For a 5-parameter, single-endpoint scrape tool with a fully documented schema, nothing material is left for the agent to guess.

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 schema already documents every parameter's meaning, which sets the baseline at 3. The description adds real value by tying useChrome, premiumProxy, premiumFallback and proxyCountry combinations to their credit costs and describing the fallback billing rule, but it does not elaborate on parameter interactions beyond pricing (e.g., proxyCountry+premiumProxy dependency is only implied).

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 ('Extract structured product data ... from an e-commerce product page') and enumerates exactly which fields come back (title, price, currency, images, brand, stock, EAN). It also names concrete target sites and explicitly positions itself above the sibling scrape_raw_html, so the agent can distinguish it without opening either 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?

Gives an explicit routing rule: 'Prefer it to scrape_raw_html for any product page.' That names the alternative and the condition selecting this tool. It stops short of saying when NOT to use it (e.g., product pages on real-estate/booking sites are covered by scrape_real_estate and scrape_booking), so the sibling set is not fully partitioned.

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 readOnlyHint and openWorldHint, so safety is covered; the description adds genuinely new operational context: a concrete cost of 30 credits, a refund policy for failed requests, and the JSON return shape. It does not cover rate limits, blocking/captcha behavior, or result-count limits per page, which keeps it below 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?

Two sentences, both dense: capability plus output shape first, then the routing alternative and cost model. No filler and nothing important buried at the end.

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 6-parameter, read-only tool with no output schema, the description gives enough (output fields, cost, refund) to call it confidently, and the detailed schema fills in query/engine/locale. Minor gaps are behavioral edge cases like pagination limits or failure modes beyond refunds.

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 every parameter including enum constraints on engine and searchType is already documented; the description adds no parameter-level detail. Baseline 3 applies since the schema carries the full semantic load.

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 (get) and resource (search engine results) and enumerates the returned content (organic results, related searches, people also ask). It also distinguishes itself from the closest sibling, scrape_raw_html, so an agent can route without opening any 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?

Explicitly tells the agent to use this instead of fetching google.com/bing.com via scrape_raw_html, which is a clear use-condition plus a named alternative. It stops short of stating when not to use it (e.g., non-search pages, or the specialized retail/real-estate scrapers), so it is strong but not exhaustive.

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?

Goes well beyond the readOnlyHint/openWorldHint annotations: ~1 minute wait, a responseId fallback, the warning that re-calling bills again, a 30-credit cost, and refunded failures. Those billing and timeout traits are exactly what an agent needs before committing to a call.

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 purpose, then the routing rule, then the scraper inventory — good ordering with no filler. It is a dense single block, though; the 17-value enumeration would scan faster as a list, and repeated parenthetical syntax makes it a wall of 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 16-parameter, no-output-schema tool this is complete: it covers per-scraper inputs, cost, timing, failure/refund behavior, and the recovery tool. Nothing an agent needs to call it once and 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?

Schema coverage is only 31% with 16 parameters, so the description carries the load — and it does, by mapping each scraper enum value to the specific inputs it consumes (e.g. 'facebookMarketplaceSearch (keyword, city, country; items_limit)'). Remaining gaps are minor: no default values, no stated behavior for irrelevant parameters passed alongside a scraper, and no format hints for 'page' or 'language'.

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 ('Scrape a public social media profile, post or search') and names all six supported networks. It also explicitly separates itself from the scrape_raw_html sibling, so an agent can route correctly 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?

Gives an explicit exclusion ('Always use this tool for these networks, never scrape_raw_html') and a follow-up path for the timeout case ('use get_social_media_result ... calling this one again is billed again'). Both when-to-use and when-not-to-use are covered, along with the named alternative.

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