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

Annotations already declare openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds context the annotations do not carry: this is a long-running job that returns an identifier rather than results, requiring polling. It omits failure semantics (per-URL errors, partial failures), 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?

Two short sentences, front-loaded with what the tool does and followed by the required next step. Nothing is wasted and no filler is present.

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 appropriately discloses the return value (a job id) and the retrieval path (poll crawl_status). It is nearly complete for a complex, heavily nested async tool; only error/failure reporting and result payload shape are left unaddressed.

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 50%, and the large `options` object contains many undocumented properties (mobile, parsers, profile, lockdown, redactPII, includeTags/excludeTags, storeInCache, etc.). The description only says 'with the same options' without explaining any of them or pointing to pagesift_scrape's option semantics explicitly as the reference.

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 list of known URLs as one job'), and the words 'list of known URLs' distinguish it from crawl-based URL discovery. It does not explicitly contrast with the single-URL sibling pagesift_scrape, so 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 gives the follow-up workflow explicitly: the call is asynchronous and should be polled with pagesift_crawl_status. It offers no explicit when-not guidance or direction to pagesift_scrape for single URLs, but the usage context is clear enough to act on.

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=false and openWorldHint=true, and the description adds genuinely new behavioral facts: the call is asynchronous and returns a job id immediately, and result payloads can be large. It stops short of explaining rate-limit behavior, cost, or what happens on partial failure, but the async contract is the critical disclosure and it is present.

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

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

Three sentences, zero filler, front-loaded with the async job contract before the tuning advice. Every sentence delivers distinct, actionable 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 an open-world async crawl tool with no output schema, the description covers the essentials an agent needs to invoke it safely: the job-id-then-poll pattern and size containment. However, with 21 parameters and nested scrapeOptions, an agent still has no description-level signal for webhook delivery, sitemap modes, query-driven adaptive crawling, or depth controls.

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?

With 21 parameters and only 43% schema description coverage, the description should compensate but mentions only three of them (limit, includePaths, excludePaths) plus an indirect nod to delay. High-impact undocumented parameters like sitemap, webhook, prompt, maxDiscoveryDepth, crawlEntireDomain, and adaptive receive no explanation anywhere in the schema or description.

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 ('start a crawl job that follows links from a URL and scrapes every page found'), which implicitly distinguishes it from the single-page pagesift_scrape. It does not explicitly name the sibling tools it supersedes, so the differentiation is inferential 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?

Gives concrete operational guidance: poll the returned job id with pagesift_crawl_status, set a conservative limit, and use includePaths/excludePaths to stay on topic. It never states when to prefer pagesift_map or pagesift_scrape over this tool, so the routing guidance is incomplete.

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, idempotentHint and destructiveHint=false, so 'Read-only' in the description adds nothing. What it does add beyond annotations is the shape of the result — status, progress, pages collected — which is useful given there is no output schema. It does not say what the status values mean or how completion is signalled.

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 short sentences, front-loaded with the verb and resource. The trailing 'Read-only' clause is redundant with annotations and is the only wasted fragment.

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-parameter polling tool with no output schema, the description covers what the call returns (status, progress, collected pages) adequately. Missing are the meaning of status values and what the agent should do on completion, which would help an agent drive a crawl loop.

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?

One parameter with 100% schema description coverage, and the schema already explains that 'id' is the job id returned by pagesift_crawl or pagesift_batch_scrape. The description adds no further meaning, 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 ('Get the status, progress and pages collected') and a specific resource (a crawl or batch scrape job), and scopes it to jobs produced by the two job-creating siblings. An agent can distinguish it from pagesift_crawl and pagesift_batch_scrape 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?

Usage is implied by the resource: poll this after starting a crawl or batch scrape. There is no explicit statement of when to use it versus re-calling the creating tool, no guidance on polling cadence, and no mention of terminal states.

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, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: URL discovery comes from sitemaps/robots.txt/homepage links and no pages are fetched, which tells the agent this is a cheap, non-rendering discovery call. It doesn't mention output volume, ordering, or rate-limit behavior, so not 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, zero filler, with the mechanism and the no-page-fetch guarantee front-loaded before the usage hint. Every clause earns its place.

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 at least imply the shape of the result (a list of URLs) and help with the ambiguous parameters. It does convey the return is URLs, but leaves the sitemap mode enum, limit semantics and subdomain/query-parameter flags unexplained for a 6-parameter 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?

Four of six parameters (limit, sitemap, includeSubdomains, ignoreQueryParameters) have no schema description at all, and the description mentions none of them. The 'sitemap' enum with include/skip/only modes is semantically load-bearing and completely unexplained, forcing the agent to guess.

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 the URLs') and resource ('of a website'), plus the mechanism (sitemaps, robots.txt, homepage links) and the key constraint 'without fetching each page'. That last clause is exactly what separates it from pagesift_scrape and pagesift_crawl without needing to open their 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?

'Use it to find the right page before scraping, or to plan a batch scrape' gives clear when-to-use context and implicitly routes agents toward scrape/batch_scrape as the next step. It never names those siblings explicitly or says when not to use this tool, so it stops short of a 5.

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

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

Annotations already declare readOnly, non-destructive, open-world behavior, so the description is not obligated to restate safety. It adds genuinely new context: robots.txt is respected and blocked pages surface as errors rather than content, which prevents an agent from misreading an empty result as a successful scrape. It does not cover caching behavior or rate/latency characteristics.

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 tight sentences: capability first, sibling routing second, a behavioral caveat last. No filler, and the most important information is front-loaded.

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

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

For a complex, 27-parameter tool with no output schema, the description covers purpose, alternatives, default output, and the robots.txt failure mode, which is enough to call it correctly in the common case. Gaps remain around caching/conditional-request semantics and browser actions, but they are secondary for the typical single-page scrape.

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?

With 27 parameters and only ~48% schema description coverage, the description needs to compensate and largely does not. It only clarifies the formats parameter (markdown is the default, plus html/rawHtml/links/images/metadata); high-impact options like proxy restrictions, engine, actions, redactPII, lockdown, zeroDataRetention, storeInCache, and conditional-request fields are left to the schema or undocumented entirely.

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 one URL, return clean content) and enumerates the default and alternative output formats. It also names each sibling it is not, so an agent can distinguish single-page scraping from batch, map, and crawl 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?

Gives an explicit selection rule: use this when you already know the page, use pagesift_batch_scrape for several known URLs, pagesift_map to discover URLs, pagesift_crawl to collect a whole site. Every alternative is named with the condition that selects it.

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