Landfall

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

Annotations already cover the safety profile (readOnly, openWorld, idempotent), and the description layers on genuinely new operational facts: a 0.05 USDC cost per completed call, automatic x402 payment, and — critically — that failed calls are never charged. That cost/charging behavior is exactly the kind of trait structured fields cannot express.

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 and return shape, then pricing. The middle enumeration of return values is long but each item is informative. No filler sentences, though the output list 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?

With no output schema, the description correctly carries the return contract (0-100 score, verdict values, tag detection, conversion paths, top 5 fixes), so an agent knows what it gets. It also covers cost and refund behavior. Minor gaps remain around latency/pagination, but the essential contract is present.

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 both parameters (url, keyword) are already documented in the schema. The description adds no syntax, format, or interpretation detail for either parameter, 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 ("Audit a landing page") plus a concrete scope ("before sending paid ad traffic"). It does not name or distinguish itself from the close siblings preview_landing_page or sample_audit, so an agent must infer the difference.

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 a clear usage trigger — run it before spending on paid traffic — which tells the agent when this tool is relevant. It offers no exclusions or explicit routing to alternatives such as preview_landing_page or sample_audit, which would be valuable given the sibling set.

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 cover safety (readOnly, idempotent, openWorld), but the description goes well beyond them: it discloses the exact price (0.01 USDC per completed call), the payment mechanism (x402 automatic payment when supported), and the failure policy (never charged if the call fails). It also reveals the shape of the output, including that each robots.txt decision comes with the rule that caused it and that a list of fixes is returned.

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 capability is front-loaded in the first sentence, followed by two short, high-value sentences on cost and failure handling. The enumeration is long but each item is doing real work by telling the agent what the report will contain.

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 returns and does so thoroughly: crawler list, per-crawler deciding rule, meta robots, X-Robots-Tag, canonical, sitemaps with entry counts and freshness, llms.txt, and fixes. The billing and failure semantics close the remaining gaps for a paid, single-URL 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?

There is a single parameter with 100% schema description coverage ('Public http(s) URL of the page or website'), so the schema already carries the semantics and the baseline is 3. The description adds no further detail such as whether a root URL is preferred over a deep page URL, but it also leaves no ambiguity.

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 precise verb+resource: check whether crawlers may read a page, and enumerates exactly what is inspected (robots.txt with Google matching rules and the deciding rule, meta robots, X-Robots-Tag, canonical, sitemaps, llms.txt, fixes). This is specific enough to separate it from check_structured_data, check_tracking and audit_landing_page even without naming 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?

The enumerated coverage implies when the tool is relevant (crawlability/indexability questions), but there is no explicit when-to-use, when-not-to-use, or routing to siblings such as full_site_report or audit_landing_page. Usage is inferable from the purpose statement rather than stated.

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

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

Annotations already cover read-only/idempotent/open-world, yet the description adds behavior they cannot express: a concrete price (0.01 USDC), the payment mechanism (x402 auto-payment, so the client must support it), and the failure-billing policy ('never charged if the call fails'). That is exactly the kind of auth/cost context an agent needs before invoking a paid 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?

Front-loaded with the core action, then a dense but purposeful clause listing checks and a final sentence on pricing. It is a single long sentence with little waste, though the feature enumeration is heavy enough that it could be broken up for scanability.

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 results and does so ('reports JSON-LD that does not parse... with a list of fixes'). Combined with annotations covering the safety profile and the schema covering the one parameter, nothing material is missing for correct 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?

There is a single parameter whose schema description already covers it fully (100% coverage: 'Public http(s) URL of the page or website'). The description adds no format or constraint details beyond the schema, so the baseline 3 for a fully-documented single param 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 precise verb+resource ('Check a page's structured data') and then enumerates exactly what is inspected: JSON-LD/microdata/RDFa items, parse failures, required/recommended properties per type, bad dates/ratings/URLs, and Open Graph/Twitter/canonical tags. That scope is unmistakably distinct from siblings like check_tracking or audit_landing_page, so an agent can select it without opening the schema.

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

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

Applicability is strongly implied by the narrow scope (use it when you need to validate schema.org markup on a URL), but the description names no alternatives and gives no explicit when-not guidance relative to audit_landing_page or check_tracking. Usage is inferable rather than stated.

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

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so safety and idempotency are covered. The description goes beyond them with substantive commercial behavior: 0.01 USDC per completed call, automatic x402 payment if the client supports it, and explicitly no charge on failure. It does not mention rate limits, auth prerequisites, or latency, keeping it out of the 5 range.

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 primary action and its return contents, then the pricing terms, with no filler sentences. The detection enumeration is long but every item is load-bearing scope information. Only minor tightening is possible.

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, so the description must convey return contents, and it does so concretely (pixel names with IDs, CMS platform, consent tools). The cost/payment mechanic is also disclosed. A little more on response shape or failure modes would be needed for a 5.

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

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

There is a single parameter with 100% schema description coverage ('Public http(s) URL of the page or website'), so the schema already carries the semantics. The description adds nothing about the url argument — no accepted forms, trailing-path behavior, or redirect handling — 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 uses a specific verb ('Check') and resource (a website's ad pixels/analytics), then enumerates exactly what is detected: Meta Pixel, Google Ads, TikTok, GA4, tag managers, consent tools, CMS platform, booking/chat tools. That is far more precise than a tautology. It does not, however, differentiate itself from the nearby audit_landing_page or sample_audit siblings, so it stops short of a 5.

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

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

Usage is implied by the scope list — an agent can infer it should call this when it needs pixel/tag detection for a given URL. But there is no explicit when-to-use, no when-not-to-use, and no mention of how this differs from audit_landing_page or preview_landing_page, which appear to overlap topically.

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 readOnlyHint/openWorldHint/idempotentHint, it discloses cost (0.5 USDC per completed call), the payment mechanism (x402), a failure guarantee ("Never charged if the call fails"), and result ordering (most problems first). That pricing and billing-safety information is exactly the context annotations cannot carry and is essential before an agent spends money.

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, payload, and the pagination instruction are front-loaded before the long parenthetical list of website deficiencies, so an agent gets the point immediately. The issue enumeration is lengthy but each item is a distinct returned signal rather than filler; only the closing cost sentence 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?

With no output schema, the description correctly carries the return-value burden by listing the fields and deficiency flags an agent will receive. Pricing, billing risk, ordering, and pagination are covered; only matters like total result counts or per-page lead density are left implicit.

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 all six parameters including enums and defaults. The description only reinforces the two required parameters' single-value semantics ("one type in one place") and the page-based batching, adding marginal 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?

"Find sales leads: independent local businesses of one type in one place" gives a specific verb, resource, and a hard constraint (one category, one location) with three concrete examples. The enumerated payload (name, address, phone, email, socials, website issues) makes it unmistakable against siblings like audit_landing_page or get_business_details, which operate on a known site or business.

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 selection context ("Ideal for agencies, web designers and outreach agents") and explains the pagination workflow with "Use page to get the next batch." It stops short of naming when to prefer a sibling such as get_business_details for a single known business, and states no 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 declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered; the description adds the non-obvious commercial and execution behaviour instead. It discloses the exact price (0.08 USDC), the payment mechanism (x402 automatic), the failure-charge policy ('never charged if the call fails'), and that all checks derive from one page read.

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 front-loaded with what the call returns before moving to audience and pricing, and every sentence carries information. The audience-targeting sentence ('agency audits, lead qualification, prospect research') is mildly promotional but still aids selection.

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 compensates by enumerating the five check categories the caller will receive, and it fully covers cost and payment preconditions. It does not describe the shape of the returned payload or any rate limits, which is the remaining gap for a paid aggregate 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 100% for both parameters (url and optional keyword with its 120-char limit), so the schema does the documentation work. The description adds no syntax, format or default detail beyond what the schema already states, making the baseline 3 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 states a specific verb and resource plus an enumerable scope: it aggregates the landing page audit, business contact details, tracking/pixel check, structured data check and crawlability check in a single call. This makes it trivially distinguishable from each of the sibling tools, which perform those checks individually.

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 choosing it ('ideal for agency audits, lead qualification and prospect research') and an economic rationale for preferring it over the individual siblings ('for less than the tools cost separately'). It stops short of an explicit when-not-to-use rule (e.g. 'use the individual check tools if you only need one signal'), so it is clear 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?

Annotations cover safety (readOnly, idempotent, openWorld), and the description adds substantial non-obvious behavior: an explicit price of 0.02 USDC per completed call, automatic x402 payment, a guarantee of no charge on failure, and the two-page crawl strategy. These cost/billing and crawl-scope details are exactly the kind of context an agent cannot get from structured fields.

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 extraction purpose and field list, then crawl behavior, provenance, and pricing in tight successive sentences. Every sentence carries distinct information with no 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?

With no output schema, the description compensates by enumerating the returned fields and disclosing the billing model and failure behavior. An agent has everything needed to decide to call it and understand the cost implications.

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 parameter with 100% schema description coverage ('Public http(s) URL of the page or website'), so the schema already fully documents it. The description adds no format or constraint detail about the URL beyond what the schema states, 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?

States a specific verb (Extract) and resource (contact and business details from a company website) and enumerates the exact fields returned. This clearly distinguishes it from siblings like audit_landing_page, check_tracking, and preview_landing_page, which are analysis/preview tools rather than data extraction.

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 internal scope (reads homepage plus contact page when the homepage lacks a phone or email), which implies when it is appropriate, but it never states when to prefer this over the sibling audit/preview tools or any exclusions. Usage is implied rather than explicitly routed.

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 openWorldHint, so the safety profile is covered. The description adds real value beyond them: the rate limit ('Limited per hour') and the shape of the result (verdict tiers, score range, issue counts, top blocker). It does not say what happens on an unreachable URL or how the limit is enforced.

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 tight sentences, front-loaded with what the tool returns before the routing hint and the rate-limit caveat. No filler and nothing redundant with the schema.

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 correctly spends words summarizing the return payload (verdict, score, counts, blocker) plus the throttling constraint. Combined with full schema coverage and read-only annotations, an agent has everything needed to call this 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?

The single url parameter is fully documented in the schema (100% coverage, with format example), so the schema carries the parameter burden. The description adds no additional syntax, constraint, or example for url; baseline 3 applies when schema coverage is high.

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 (preview/quick check), resource (landing page), and the concrete payload the caller gets: verdict, 0-100 score, issue counts, top blocker. It clearly distinguishes itself from audit_landing_page as the lightweight version.

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 names the alternative (audit_landing_page) and the condition that selects it ('for the evidence and fixes'), so an agent knows this tool is the fast triage call and the sibling is the deep-dive. It also flags the per-hour limit, which shapes call-frequency decisions.

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, idempotent, closed-world). The description adds genuinely useful context beyond them: the returned data is synthetic and it mirrors the exact field set of the paid audit, which stops an agent from treating the output as a real audit result.

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 sentence, front-loaded with the action and resource, with the two qualifiers (fictional page, full field parity with the paid audit) appended efficiently. Nothing is wasted.

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's promise of 'every field the paid audit returns' is the main signal about the return value, which is adequate for a zero-argument sample tool. It could say more about format or size, but nothing needed to invoke it correctly is 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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies no input is required by describing a canned sample, and there are no parameters for it to document.

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 (returns an example audit report) and adds the key qualifier that the page is fictional. It implicitly differentiates from audit_landing_page by being the sample/free variant, but never names the siblings, so an agent must infer the distinction from context rather than being told.

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 word 'example' and 'fictional page' imply this is for inspecting the report shape rather than auditing a real page, but the description never states when to choose it over audit_landing_page or preview_landing_page. Usage 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.