AI-operated. Email authentication reader: six free tools, no key, no signup.

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

Annotations already mark it read-only, idempotent, and non-destructive; the description adds important context: it is AI-operated, requires no account, takes no payment, and returns a link that a person must open and pay at. It also explicitly disclaims promises of citation, which is valuable behavioral guidance beyond the annotations.

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 dense and runs through a long enumerated list of audit report contents before reaching the use-case guidance; it could be significantly more scannable with bullets or shorter sentences. However, most clauses carry real constraints, so it is not padded or irrelevant.

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?

Even without an output schema, the description explicitly states what will be returned: the price, what is read, what is promised, and the checkout link. Combined with the fully documented optional parameter, strong annotations, and explicit use cases, nothing needed to invoke this tool 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 schema already covers the single optional `domain` parameter completely, including that it is just echoed for convenience and that the actual audited domain is typed at checkout. The description reinforces 'single domain' but does not add meaningful semantics beyond the schema, so the baseline score of 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 title and description both name a specific deliverable: the price, terms, and checkout link for an AI answer-engine readability audit of a single domain. It also clearly distinguishes itself from email-authentication tools and states what it is not ('does not start an audit'), so an agent can separate it from 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?

The description explicitly says 'Use this when a caller asks whether ChatGPT, Claude, Perplexity or Google's AI can read their site...' and provides negative boundaries such as 'NOT A PROMISE OF CITATION' and 'DOES NOT TAKE PAYMENT'. It also names the email-authentication tool family as a different subject, giving clear when-to-use and when-not-to-use guidance.

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

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

Even with readOnlyHint and idempotentHint annotations, the description adds critical behavioral context: it does not take payment, does not start an audit, and returns a link a human must open. It also discloses that the audit reads from public DNS and lists the eight defect classes, going well beyond the annotations.

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 long but structured and information-dense. The extensive RFC-clause listing is purposeful because the tool's output is expected to describe what is checked. The key usage caveats are appropriately emphasized in caps, and front-loaded content is clear.

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

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

For a simple one-parameter read-only quotation tool, the description covers pricing, terms, deliverable contents, when to use it, when not to use it, and the actual behavior. An output schema exists, so return-value details need not be repeated, and nothing essential 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?

Schema coverage is 100% for the single optional domain parameter, so the baseline is 3. The description adds extra value by clarifying that the parameter is only echoed back for convenience and that the domain actually audited is the one typed at checkout.

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: it returns the price, terms, and checkout link for a one-off paid audit of a single domain. It clearly differentiates itself from the free reader siblings by naming them and framing this as the paid option.

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?

Explicit when-to-use guidance is present: 'Use this when a caller asks what a full audit costs, asks for a written report... or asks for the paid option.' It also explicitly instructs to run the six free readers first and lists them by name, giving clear 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 readOnly and idempotent, and the description adds live public DNS reads, two independent resolvers, and full tag parsing. This adds useful context beyond the structured annotations without contradicting them.

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

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

The description is compact and information-dense, leading with purpose and use cases. The 'Operated by an AI, not a person' opener is slightly odd but does not bloat the 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?

With one fully documented parameter, safety annotations, and an output schema, the description covers what the tool does, when to call it, and how it executes. Nothing essential to correct invocation 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 schema already documents the domain parameter well, including a bare domain example and no scheme/path constraints. The description adds the meaningful detail that the domain is looked up at _dmarc.<domain>, clarifying how the parameter is used even though schema coverage is complete.

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 exact resource (_dmarc.<domain>), a specific action (Read), and the concrete outputs (p, sp, pct, rua, ruf). The 'Use this when' trigger questions clearly separate it from related email-auth siblings like spf_check and mta_sts_check.

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 explicitly lists when to use the tool: checking a domain's DMARC policy, spoofing protection, misconfiguration, or aggregate report destinations. It does not name alternatives or state when not to use it, so it stops short of full 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?

Beyond the annotations, the description discloses important runtime behavior: it always issues a second query with a synthetic sender label to detect wildcard authorizations, reads live DNS, does not send email, and stores nothing. This materially helps an agent predict side effects and interpret results beyond what readOnlyHint alone would convey.

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 longer than average, but every sentence carries useful detail: the RFC reference, the wildcard second query, the four outcome classes, and the no-storage guarantee. The most critical behavioral warning is emphasized with capitals, making it easy to notice.

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 compensates by enumerating the four possible findings. It also covers the unusual wildcard ambiguity, explains that DNS is queried live, and confirms no data is stored. Together with the schema's domain parameter, this gives an agent enough to call the tool 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 schema already defines the domain parameter, and with 100% schema coverage the baseline applies. The description adds context by explaining that the domain's DMARC record is read and that each external destination is checked, but it does not need to redefine the parameter format.

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, non-obvious operation: validating the RFC 7489 external-destination authorization for a domain's DMARC rua/ruf targets. It explains input (DMARC record), mechanism (querying the authorization TXT record), and distinct outcomes, leaving no ambiguity about what the tool does.

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 explicit use cases: 'Use this when asked whether a DMARC reporting provider is authorized, whether a report destination is legitimate, or what the _dmarc.<domain> TXT record means.' It does not name sibling tools or state when not to use it, but the guidance is clear enough to route an agent correctly.

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 readOnlyHint and idempotentHint annotations, the description discloses that the tool is operated by an AI, reads live public DNS at call time, is free, checks two independent resolvers, and includes contextual paid-monitoring links without withholding results. This is rich behavioral transparency with no contradiction.

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 longer than average but every sentence contributes: purpose, behavior, usage, and monetization transparency. It is front-loaded with the core value proposition and uses plain language, though it could be slightly 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?

Given the presence of a rich output schema, complete parameter schema, and strong annotations, the description fully rounds out what an agent needs: what the tool checks, how it behaves, when to choose it over siblings, and what to expect in the response.

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 input schema already documents the single parameter fully, including format guidance and an example. The description adds broader context about what the parameter affects but not much beyond the schema, so the baseline score of 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 names a specific verb and resource: it reads both SPF and DMARC together and answers concrete questions about spoofing exposure and deliverability. It also distinguishes itself from siblings like spf_check and dmarc_check by explicitly being the combined 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?

The description explicitly states when to use the tool: 'Use it when you want both records rather than one.' This gives clear routing guidance against the sibling tools that check SPF or DMARC separately.

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, idempotentHint=true, destructiveHint=false. The description goes beyond by disclosing network behavior: it makes eleven requests in one pass, reads only the fixed paths, calls no target tools, follows no links, stores no result, and identifies itself as omnia-mcp-check. It also states the operator is an AI and that it refuses certain host types, adding operational context annotations cannot convey.

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 dense and front-loads the core purpose early (first sentence after the AI-operator note). It is longer than average but every clause carries information about behavior, output, or restrictions. Minor non-essential details like 'Free, no key, no account' and the opening 'Operated by an AI, not a person' keep it from a perfect 5.

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 tool with no output schema, the description is strikingly complete: it explains input requirements, what the tool reports (initialize result, tools/list names + description presence, HTTP status of nine specific discovery documents), the number of requests, and refusal conditions. An agent can predict behavior and set expectations without any additional schema.

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 input schema already fully describes the single 'url' parameter (100% coverage), so the baseline is 3. The description adds meaningful constraints on the parameter: it must be a public https MCP endpoint, and it rules out IP literals, private/local names, and *.workers.dev hosts. This helps the agent pre-validate inputs, raising the score above baseline to 4.

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?

Description states a specific verb+resource: 'Point this at any public https MCP endpoint and it reports what an unauthenticated indexer would record about it.' It enumerates the exact outputs (initialize result, tools/list summary, HTTP status of nine discovery documents), making it clearly distinct from the unrelated email/DNS sibling tools.

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

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

Explicit use cases are given: 'Use it to find out why a server is listed badly or not at all, or to check your own before you publish it.' It also specifies when not to use by listing refusals (non-https, IP literals, private/local names, *.workers.dev), which serves as implicit exclusion guidance. Siblings are in a different domain, so no alternative routing is needed.

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 adds meaningful behavioral context beyond the annotations: it is operated by an AI, reads live at call time, caches nothing, and is evaluated against RFC 8461 and RFC 8460. This is valuable transparency about side effects and freshness that the readOnly/openWorld/idempotent annotations do not fully convey.

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

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

The description is compact but information-dense, front-loading the tool's core action and supported features. Every sentence adds distinct value: the resource list, the return fields, the use cases, the RFC grounding, and the live/no-cache behavior. There is no filler or repetition.

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 a single parameter, a rich output schema, and annotations covering the safety profile, the description covers everything needed to invoke the tool correctly: what it checks, the return values, and when to use it. No critical context is missing for an agent deciding to call 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?

The input schema already provides 100% coverage for the single 'domain' parameter, including the bare-domain constraint and an example. The description reinforces how the domain is used in record lookups, but it does not add significant new semantic meaning beyond what the schema already 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?

The description uses a specific verb ('Read') and names the exact resource: MTA-STS announcement TXT record, policy file, and TLS-RPT record. It clearly distinguishes this tool from sibling email-auth tools by focusing on MTA-STS and TLS-RPT, so an agent can tell it apart from dmarc_check, spf_check, and email_auth_check.

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 explicitly lists concrete use cases: checking whether a domain enforces TLS for inbound mail, determining MTA-STS mode, diagnosing why a policy is not applied, and finding TLS failure report destinations. It does not explicitly name sibling alternatives or state when not to use this tool, so it stops just 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 mark the tool readOnly, idempotent, and non-destructive. The description adds substantial behavioral context beyond that: it is AI-operated, does not take payment, does not start a read, and returns a link a human must open and pay at. Pricing and non-committal terms are also disclosed. No contradiction with annotations.

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 longer than average but every sentence carries routing or behavioral information that an agent needs. It front-loads the core return value and then covers alternatives, pricing, and exclusions. Slightly dense, but not wasteful.

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 an output schema exists and annotations cover safety, the description is complete for correct invocation: it explains purpose, scope, price, terms, alternatives, and that no read or payment occurs at this step. Nothing material is missing for an agent to decide when and how to call this 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?

The single optional parameter already has 100% schema description coverage. The description adds valuable nuance by stating the domain is only echoed back for convenience and is not used to determine which domains get read, clarifying an otherwise potentially confusing parameter.

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

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

The description clearly states the tool returns the price, read scope, terms, and checkout link for a paid ROSTER read of up to 25 domains. It explicitly disambiguates this from actually running a read and from single-domain audit_order, making its function unmistakable even 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?

It gives explicit when-to-use guidance: callers asking about MANY domains, portfolios, groups of brands, or bulk/multi-domain costs. It also names the alternative audit_order for single domains and instructs to run the six free readers first, providing clear routing against every sibling.

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 well beyond the annotations by disclosing live public DNS reads, two independent resolvers, a one-minute cache limit, and the RFC-based lookup counting behavior. The annotations already declare read-only, idempotent, and open-world hints, and the description adds valuable operational detail without contradicting any of them.

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

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

The description is front-loaded and information-dense, covering purpose, use cases, return behavior, and execution context. The phrase 'Operated by an AI, not a person' adds little, and the return-value list partly duplicates the output schema, so it is not perfectly concise, but it still earns its length.

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 read-only DNS tool, the description covers purpose, validity rules, return contents, live-data behavior, caching, and use cases. The output schema handles the return structure, so the description is complete for an agent to select and invoke this tool 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 schema already fully documents the single 'domain' parameter with an example and constraints. The description does not materially expand parameter semantics beyond calling it the domain an SPF record is read from, so the baseline of 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 and resource: 'Read the SPF record a domain publishes in DNS' and 'count the DNS lookups'. It clearly distinguishes itself from the sibling DNS tools like dmarc_check and mta_sts_check by focusing exclusively on SPF, and it names the RFC 7208 limit precisely.

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 explicitly lists concrete triggers: when asked whether an SPF record is valid, why mail fails SPF, whether the ten-lookup limit is exceeded, or what the record contains. It does not name sibling tools as alternatives, but the provided use cases are clear enough to route an agent correctly.

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 well beyond the annotations by explaining the tool is AI-operated, returns a checkout link rather than starting a watch, requires a person to pay, and begins the watch only after payment. It details the monitoring behavior, alert conditions, baseline email, and pricing, all of which are not visible in annotations.

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 longer than average, but it earns the length by covering purpose, pricing, cancellation, alert behavior, and usage guidance. It is front-loaded with the core purpose and caveats, though the philosophical explanation about DNS records being a state rather than a fact is not strictly necessary.

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 paid subscription-related tool, the description covers price, terms, cancellation, what the watch monitors, alert format, and the crucial limitation that this tool does not start a watch. The optional parameter and absence of required input are fully clarified, and the output schema exists to define the return shape, so nothing essential 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 input schema already documents the single optional 'domain' parameter with examples and a clear description. The tool description echoes that the domain is echoed back and does not start anything, which adds no significant semantic meaning beyond the schema. With 100% schema coverage, the baseline of 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 states a specific resource ('checkout link for a paid daily watch on ONE domain') and a distinct scope, clearly separating it from the free reading tools. It also explicitly says what the tool does not do, which removes ambiguity about its role.

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 explicitly says 'Use this when a caller asks to be told IF a domain record CHANGES, to monitor or watch a domain, or asks what this costs.' It contrasts with the free reading tools and clarifies the tool only returns a link, not a watch, giving clear when-to-use and when-not-to-use guidance.

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

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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses that no JavaScript executes, no browser is used, no account/key is required, and the tool never charges or takes payment. It also explains the behavioral consequence of no JavaScript execution, which is directly useful to callers.

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 long but front-loaded with the most important facts: free, no key, no account. Every sentence contributes useful operational context, though the full-extraction pricing and URL details could have been slightly more compact without losing value.

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 one parameter, no output schema, and strong annotations, the description fully compensates by enumerating the returned fields (HTTP status, final URL, byte count, title, character count, headings, JSON-LD, links, first 400 characters) and clarifying the no-JavaScript limitation. The tool is completely understandable without additional context.

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

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

Schema coverage is 100%, and the schema already describes 'url' as an absolute https address with a concrete example. The description confirms 'one public web page' but adds no further parameter-level semantics beyond what the schema provides, so the baseline of 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 and resource: it 'fetches one public web page and returns what a text extractor gets from it,' then enumerates the exact output fields. It clearly differentiates this preview tool from the separate paid full-extraction call, and the sibling tools are in a different email/security domain, so there is no ambiguity.

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 explicitly distinguishes the free preview from the full extraction, naming the alternative as a separate paid HTTP call with its own URL. It also gives a concrete diagnostic use case: if a page renders text only via JavaScript, the low character count itself tells the caller whether the page is readable without a browser.

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