ScraperWatch

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 the data source (saved 30-day aggregates), the qualifying thresholds (300+ runs, 20+ users), that evidence includes snapshot date and age, and explicitly disclaims live testing or currency guarantees. It lacks any note on auth requirements or read-only nature, but the staleness/limitation disclosure is strong.

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 and thresholds are front-loaded in the first clause, with the caveat sentence following naturally. It is dense but every element (thresholds, alternatives, snapshot age, live-test disclaimer) earns its place; 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?

No output schema and no annotations exist, so the description must explain returns, and it does: it names the primary pick, the alternative categories, and the evidence fields (snapshot date and age). The remaining hole is the undocumented 'site' parameter, which keeps it short of 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?

There is one required parameter, 'site', with 0% schema description coverage, so the description must compensate. It never mentions the parameter at all, leaving ambiguous whether 'site' is a domain, a hostname, a website ID from list_websites, or a display name. This is a real gap for the only input.

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 (Recommend) and resource (scrapers/tools for a site), and enumerates the selection criteria: highest recorded success rate among tools with 300+ runs and 20+ users, plus most-used and cheapest alternatives. It is distinguishable from compare_* siblings (which compare) and find_scrapers (which locates), though it never names them 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 description implies usage context by framing results as historical aggregate recommendations (-day window) that are explicitly not a live execution test, which tells the agent when the data is trustworthy. However, it never states when to prefer this over siblings like compare_scraping_apis or find_scrapers, and gives no prerequisites or exclusions.

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 establish a safe read-only, closed-world operation, and the description reinforces that with 'no live lookup' and 'free cached'. It adds real value beyond annotations: unknown costs are not fabricated, observed dates and cautions are included, and the Webshare affiliate link is disclosed. Return-shape and staleness thresholds are still implicit.

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?

Four dense sentences with no filler, and the core purpose is front-loaded ahead of the caveats. The telegraphic phrasing ('Full captured package bills only', 'unknown costs stay unknown') is efficient but slightly terse for first-time readers.

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 the comparison returns (observed dates, sources, cautions, disclosed affiliate link) and what it excludes. It is largely complete for a read-only cached pricing tool, though it doesn't explain ordering or how offers are ranked.

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 0%, so the description carries the burden, and it does name both parameters plus the 'positive' constraint on monthly_gb. However, it omits the enum values (residential, datacenter, isp_static_residential, mobile) and any unit/precision guidance for GB, leaving half the semantic load on 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: comparing proxy pricing offers, filtered by product type and monthly GB. Its domain is clearly distinct from siblings like compare_scraping_apis and compare_rag_extractors, but it never explicitly names or routes away from them, so the differentiation is inferred rather than stated.

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?

Strong scoping signals: free cached data, no live lookup, full captured package bills only, per-IP offers handled separately. That tells the agent when this tool's output is appropriate, but it gives no explicit when-to-use-vs-alternative routing.

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 the safety profile (readOnly, non-destructive, closed-world), so the bar is lower. The description still adds real value: 'No provider requests' clarifies this reads saved/cached data rather than hitting providers, and 'unknown measurements are null' discloses the missing-data behavior.

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

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

Only two sentences, but they are overloaded with cryptic phrases like 'named legacy literal table rates' and 'hash-verified escaped-underscore audit', and the clause 'The legacy table gap is not demonstrated structural loss' is a disclaimer that does not clearly earn its place in a front-loaded definition.

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?

It gestures at what is returned (measurements, source dates, audit, limitations, disclosed buyer links) and there is no output schema to lean on, so some coverage is needed. But the obscurity of the legacy-table and audit references leaves the agent unsure what the tool actually produces or when it is the right choice.

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

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

The tool takes zero parameters, so the schema has no parameter semantics to convey and the baseline is 4. There is nothing the description could add about inputs.

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

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

The verb 'Read saved ... extraction measurements' and the resources (Firecrawl, Jina Reader, DIY RAG) give a workable sense of the tool, and it is nominally distinct from siblings like compare_proxy_providers and compare_scraping_apis. However, the purpose is buried under dense jargon ('named legacy literal table rates', 'hash-verified escaped-underscore audit') that obscures what is actually being compared.

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 a faint hint that the legacy/audit data is 'otherwise unavailable/stale', implying this is the only route to it, but there is no explicit statement of when to use this tool versus the sibling comparison tools. No exclusions, prerequisites, or alternative routing are given.

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 the safety profile (readOnly, non-open-world, non-destructive), and the description adds real value on top: no live requests are made, unknown/excluded IDs and duplicates are surfaced explicitly, and results carry snapshot age, billing caveats, and affiliate disclosure. It stops short of describing ordering guarantees beyond 'caller order' or the result shape.

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 the compare purpose and scope, and no sentence is obviously filler. The telegraphic, jargon-heavy phrasing ('compatible standard result-event rates', 'eligible success statistics') is dense but not padding.

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 single-param, read-only tool with no output schema and annotations covering safety, the description covers constraints, behavior (no live runs), input handling (duplicates/unknown IDs), and return caveats. Only the precise comparison output structure is left unstated.

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

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

The sole parameter has zero schema description coverage, so the description must carry the meaning. It does so by specifying 'exact actor IDs', the 2-5 range matching min/maxItems, 'caller order', and that duplicates/unknown IDs are reported explicitly — genuinely adding semantics beyond the bare array 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?

Names a specific verb+resource ('Compare ... exact actor IDs') and pins the scope to 'two to five'. It is distinguishable from same-family comparators (compare_scraping_apis, compare_proxy_providers) by resource, though it never explicitly contrasts itself with them.

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: the metric restrictions ('saved usage, eligible success statistics...') and 'No actor runs or live requests' hint at when this is appropriate, but there is no explicit when-to-use, when-not, or named alternative such as find_scrapers or best_scraper.

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 it does disclose key traits: the data is 'saved'/'historical' and 'No vendor requests' is made, which tells the agent this is a cached, read-only-style operation. It also flags 'limitations and affiliate disclosure' in the output, but says nothing about freshness, update cadence, or access requirements.

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?

It is a single sentence, which is economical, but it reads as a run-on list of output artifacts ('content checks, latency population, limitations and affiliate disclosure') rather than a front-loaded statement of purpose. The action is not front-loaded; the content inventory is.

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 usefully enumerates what the response contains and notes the absence of vendor requests, which is needed context. However, for a comparison tool with several confusingly similar siblings and no annotations, the lack of any usage routing or freshness/caveat detail leaves meaningful 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?

The tool takes zero parameters, so the baseline is 4. There are no arguments whose semantics the description could clarify or omit.

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 specific resources (ScraperAPI/ScrapingBee comparison) and distinguishes itself from siblings like compare_proxy_providers, but it is framed as a description of returned data rather than a clear verb+resource statement of what the tool does. An agent can infer it surfaces a saved comparison, but the purpose is buried in a dense noun phrase.

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 explicit when-to-use or when-not-to-use guidance, and no alternatives are named despite several sibling 'compare_*' and 'best_scraper' tools that could be confused with it. The only implicit cue is 'No vendor requests,' which hints it uses saved data rather than live lookups.

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 that rankings come from saved 30-day aggregate data with a snapshot date/age rather than a live execution test, which prevents the agent from over-trusting results. It omits return shape, pagination/limit behavior, and any auth or rate-limit constraints, so it is not exhaustive.

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 action is front-loaded in the first sentence, followed by the evidence caveat and then per-parameter rules. Four dense sentences, each carrying informatio not present in structured fields; minor awkwardness in embedding a schema-style constraint sentence inside prose.

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 or annotations exist, so the description must stand alone; it covers purpose, ranking inputs, data provenance, and the trickiest parameter. It leaves 'limit' semantics and the shape of returned results unaddressed, which is a modest gap for a 3-param discovery 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 description coverage is 0%, so the description must compensate, and it does for the two non-obvious params: min_success_rate's finite 0-1 inclusive range and the zero-vs-positive 'unknown rate' rule, plus site with concrete domain/name examples including multi-word inputs. The 'limit' parameter is never mentioned, leaving one of three params unexplained.

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 ('Rank ready-made scrapers') plus the ranking criteria (30-day usage, success rate, price), which is concrete enough to distinguish it from a single-pick tool like best_scraper. It never explicitly names a sibling or contrasts itself with best_scraper/compare_scraping_apis, so the differentiation is implied rather than stated.

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 the nature of the ranking data but gives no guidance on when to reach for this tool versus best_scraper or the compare_* siblings. There are no stated prerequisites or exclusions; the 'snapshot, not live test' caveat is useful context but is not usage routing.

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 disclose the returned metrics and the 30-day window. It says nothing about scope (all tracked sites vs. the caller's own), authentication requirements, or result size/pagination limits, which is a meaningful gap for an unannotated tool.

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

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

One front-loaded sentence with no filler; every clause (tracked websites, scraper count, 30-day users) earns its place and directly describes the payload.

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?

An output schema exists, so return formatting is already covered, and the description adds the semantic meaning of those fields (scrapers per site, 30-day users). For a simple read-only list tool this is nearly complete; only scope/auth behavior is left unstated.

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

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

The tool takes zero parameters, so there is nothing to document and the baseline of 4 applies. The description correctly does not invent parameter guidance that isn't needed.

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

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

States a specific verb (List) and resource (the websites ScraperWatch tracks), and adds what each row contains. It implicitly separates itself from find_scrapers and best_scraper by operating on websites rather than scrapers, but it never names or contrasts those 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?

Usage is only implied — the description tells the agent what it gets back, not when to reach for this over find_scrapers. For a zero-parameter list tool the intent is largely self-evident, so this is minimum-viable rather than misleading.

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