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

No annotations are provided, so the description carries full burden. It explicitly discloses 'Safe, read-only diagnostic evaluation. No file modifications,' which is a clear behavioral statement beyond the tool name and schema.

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

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

The description is well-structured with purpose, usage guidelines, and behavioral transparency sections. Each sentence provides useful context without fluff or redundancy.

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 simple single-parameter input and no output schema, the description sufficiently explains what the tool evaluates and when to use it. It provides enough context for an agent to correctly select and invoke the 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%, so baseline is 3. The description does not add further parameter semantics beyond the schema, but none are needed given the single simple 'target' 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 audits content for Answer Engine Optimization, with specific evaluation criteria. It distinguishes itself from sibling tools by naming seo_audit_geo and seo_audit_onpage as alternatives for different use cases.

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 states when to use ('when optimizing content to win conversational AI search citations...') and when not to use, with concrete alternative tool names for excluded scenarios.

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 explicitly states 'Safe, read-only content analysis. No file modifications.' Even though no annotations are provided, the description discloses the behavioral traits of safety and read-only nature.

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 concise, listing key evaluation criteria in a single sentence, followed by clear usage guidance and safety note. It is well-structured and front-loaded with the main purpose.

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 tool's straightforward nature and lack of output schema, the description is sufficiently complete. It covers what the tool does, when to use it, and its safety profile. No additional context seems necessary.

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 fully describes the 'target' parameter (URL or file path). The tool description does not add additional parameter-specific information, so it does not exceed the baseline for high schema coverage.

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 evaluates content depth, search intent classification, word count, thin content, reading ease, and E-E-A-T signals. It is specific about the function and distinguishes it from generic audits.

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 (analyze article/landing page editorial quality) and when not to use, with alternatives for schema validation and marketing strategy. This provides clear guidance for tool selection.

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?

No annotations are present, so the description carries the full burden of behavioral disclosure. It explicitly says 'Safe, read-only CRO analysis. No file modifications,' which fully communicates the tool's safety profile. This is a sufficient and unambiguous disclosure for a read-only audit operation.

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 well-organized into purpose, usage guidelines, and behavioral transparency sections. The main sentence front-loads the verb and object, followed by a compact list of audited signals. Every line earns its place and there is no redundant fluff.

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, the description is nearly complete: it covers what the tool audits, when to use it, alternatives, and safety. The only missing piece is the output format, but given the sibling 'seo_audit_*' family, an agent can reasonably infer the result is an audit report. This is a minor gap.

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

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

The input schema already fully describes the only parameter 'target' as a live URL with an example. The tool description does not add additional parameter-level detail, though its usage guidelines hint at appropriate target URLs (landing pages, pricing pages, funnels). This is a standard baseline case where the schema does the heavy lifting.

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 opens with a specific verb ('Audits') and a specific resource ('Conversion Rate Optimization (CRO) and user conversion signals'), then enumerates concrete signals it checks (CTAs, contact channels, social proof, floating buttons, risk reversal). It also explicitly distinguishes itself from organic-ranking audit tools by naming seo_audit_onpage and seo_audit_technical as alternatives.

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 'USAGE GUIDELINES' section clearly states when to use the tool (landing pages, pricing pages, checkout/contact funnels) and when not to use it (organic ranking signals), naming the exact alternative tools. This gives the agent explicit routing rules with no left to inference.

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?

No annotations are provided, so the description carries the full behavioral burden. It directly discloses safety-relevant behavior: 'Safe, read-only diagnostic evaluation. No file modifications.' This is meaningful beyond the schema and covers the most important behavioral trait for an audit tool. It could add more detail about return format or failure behavior, but the disclosed safety profile 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 description is well organized with clear sections: main purpose, usage guidelines, and behavioral transparency. It is front-loaded with the primary purpose, and every sentence earns its place. Despite covering multiple concepts, it remains tight and scannable.

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 one required parameter with full schema coverage, no output schema, and no annotations, the description provides a complete picture: what the audit evaluates, when to use it, when not to use it, which sibling alternatives apply, and that it is read-only. Nothing essential for correct selection or 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?

Schema description coverage is 100% and the single 'target' parameter is described in the schema as 'URL (e.g. "https://example.com") or local file path to audit.' The description does not add additional parameter-level semantics, but the schema already documents the parameter fully. 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 ('Audits') and resource ('Generative Engine Optimization (GEO)') and enumerates concrete evaluation areas: brand/organization entities, Schema.org definitions, sameAs knowledge graph reconciliation, and Author E-E-A-T credentials. It is clearly differentiated from siblings by naming what this tool addresses versus seo_audit_local and seo_audit_aeo.

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 when to use the tool ('Use to evaluate how LLM-based search engines comprehend brand identity and authority') and provides two explicit exclusions with named alternatives ('Do NOT use for local map pack NAP consistency; use seo_audit_local instead' and 'Do NOT use for direct answer snippet definitions; use seo_audit_aeo instead'). This is exemplary routing 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explicitly states 'Safe, read-only link graph analysis. No file modifications,' directly informing the agent that invocation has no side effects. This is strong transparency for a tool with no annotation metadata.

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 short labeled sections front-load the main purpose and place usage and safety notes in scannable bullets. Every sentence earns its place, with no redundancy or filler.

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

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

For a one-parameter, read-only audit tool, the description covers what it does, when to use it, what not to use it for, and its safety profile. The described artifacts (generic anchor text, orphan pages, suggested links) set clear expectations even without an output 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?

Schema coverage is 100% and the schema already describes target as a live URL or local file path. The description reinforces that the target is the subject of an internal-link audit but does not add new parameter-level meaning such as format constraints, defaults, or additional usage examples.

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 opens with a specific verb-resource pair ('Audits internal linking structure') and lists concrete outputs (generic anchor text, orphan pages, link suggestions), making it clearly distinct from the many seo_audit_* siblings. Even without naming each sibling, the internal-link focus is unambiguous.

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 usage bullets state when to use the tool ('to improve PageRank flow, internal topic clustering, and anchor text relevance') and when not to use it ('Do NOT use to inspect external backlink profiles'). It directly names seo_suggest_related_ecosystem as the alternative for off-page targets, leaving no ambiguity about 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?

No annotations are provided, so the description carries the full burden of safety disclosure, and it delivers the most critical trait: 'Safe, read-only diagnostic evaluation. No file modifications.' It also frames the tool as diagnostic, implying no side effects. It could additionally disclose whether live network requests are made to the target or whether authentication is required, but the core safety-relevant behavior is explicitly covered.

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 tightly organized with labeled sections (USAGE GUIDELINES, BEHAVIORAL TRANSPARENCY) and bullet points. The opening sentence is dense but purposeful, listing the audit checks without padding. Every sentence and bullet earns its place; there is zero filler.

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

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

For a one-parameter, read-only diagnostic tool with no output schema, the description covers the selection-critical dimensions: what checks are performed, who should use it, exclusions with alternatives, and safety. The only notable gap is the absence of any hint about the return format — since no output schema exists, a brief note on what the audit report contains would make it fully complete. Minor given the tool's simplicity.

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% — the single required 'target' parameter already has a schema description ('Target live URL... or local file path to audit'). The description adds no parameter-level detail beyond the schema, so the baseline of 3 applies. The tool description focuses on audit scope rather than what values target should take, which is acceptable given full schema coverage.

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 ('Audits') and resource ('Local and Area SEO'), then enumerates concrete evaluation targets: LocalBusiness Schema.org JSON-LD, NAP consistency, click-to-call links, Google Maps embed signals, and doorway city page duplication. This level of specificity makes the tool clearly distinguishable from the other seo_audit_* siblings, whose names alone do not convey this local focus.

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 states when to use it ('local business websites, multi-location practices, and regional service providers'), when not to use it ('pure SaaS, digital-only, or non-geographic websites'), and names alternatives ('seo_audit_technical' or 'seo_audit_onpage'). This is the exact when/when-not/alternatives structure the rubric rewards, leaving nothing to inference.

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 provided, the description carries the full burden, and it explicitly states 'Safe, read-only diagnostic evaluation. No file modifications.' This clearly discloses the tool's non-destructive behavior, which is essential for an agent deciding whether invocation is safe.

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 well-structured with clear sections for purpose, usage guidelines, and behavioral transparency. Every section earns its place, and the most important information is front-loaded in the opening sentence.

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 audit tool, the description covers purpose, usage boundaries, and safety. It does not explicitly describe the output format or return shape, but the absence of an output schema and the simplicity of the tool make this a minor gap rather than a serious omission.

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 the only parameter, target, is already documented as a live URL. The description does not add new semantic detail about the parameter itself, 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 uses a specific verb ('Audits') and resource ('on-page SEO elements'), then enumerates concrete checks like title tag length, meta description, H1-H6 hierarchy, OpenGraph, and Twitter cards. This clearly distinguishes it from siblings such as seo_audit_technical and seo_audit_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?

The description explicitly states when to use the tool ('when evaluating page-level metadata, heading structures, and social sharing previews') and provides direct exclusions with named alternatives for technical indexing and structured data validation. This leaves no ambiguity about tool selection.

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?

No annotations were provided, so the description carries the burden. It states the tool is safe, read-only, performs no file modifications, and does static analysis rather than browser rendering, which discloses key behavioral traits. It does not mention rate limits or output format, but for a diagnostic tool this is adequate.

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 organized into clear sections with front-loaded purpose and uses bullets for guidelines and transparency. It is concise and every section 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?

For a single-parameter read-only diagnostic tool, the description provides sufficient context for selection and invocation: target format is documented, use cases and exclusions are stated, and safety is disclosed. No output schema exists, but the absence of output expectations is a minor gap for a tool whose core behavior is clear.

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 documents the single parameter 'target' as a live URL or local file path, so schema coverage is 100%. The description adds no additional parameter semantics beyond what the schema provides, meeting the baseline of 3.

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 ('Identifies') and resource ('code-level Core Web Vitals risks'), enumerating CLS, LCP, and render-blocking scripts. It differentiates from siblings by emphasizing static source analysis rather than browser benchmarking, making it distinguishable from other seo_audit_* 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?

Explicitly states when to use (static HTML/template performance defects) and explicitly warns not to use for real-time synthetic browser benchmarks like Lighthouse. This gives clear routing criteria vs alternatives.

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?

No annotations are provided, so the description carries the full burden, and its BEHAVIORAL TRANSPARENCY section delivers: 'Safe, read-only network/file inspection. Fetches robots.txt and sitemap.xml without modifying them.' This clearly discloses the non-mutating safety profile. It falls short of a 5 only by omitting details like rate limits, auth requirements, or behavior when robots.txt/sitemap.xml are missing.

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 definition is organized into labeled sections (USAGE GUIDELINES, BEHAVIORAL TRANSPARENCY) with the core purpose front-loaded in the first sentence. Every sentence earns its place: the scope enumeration, the bot-specific context, the exclusion with alternatives, and the safety note are all non-redundant.

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

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

For a multi-faceted audit tool with a single parameter and no output schema, the description covers purpose, scope, exclusions, and safety quite thoroughly. It is missing only the expected return format and target URL format, which an output schema would normally clarify. The absence of failure-behavior notes is also a minor gap.

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

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

Schema description coverage is 100% for the single required 'target' parameter, so the baseline is 3. The description adds mild context by implying target is the site whose robots.txt and sitemap.xml get fetched, but it never explicitly states the expected format (e.g., full URL vs. domain, protocol requirement). The schema does the heavy lifting here.

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 opens with the specific verb 'Inspects' and enumerates concrete objects: robots.txt allow/disallow rules per user-agent, sitemap index validity, contradictory directives, and HTTP security headers. This level of specificity fully differentiates it from siblings like seo_audit_sitemap_multipage and seo_crawl_and_extract without needing to open any 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?

The USAGE GUIDELINES section provides explicit positive context ('Use to inspect crawl configuration and indexation guardrails for Googlebot, GPTBot, ClaudeBot, and PerplexityBot') and an explicit negative exclusion with named alternatives ('Do NOT use for crawling page body content; use seo_audit_sitemap_multipage or seo_crawl_and_extract instead'). This is exactly the when/when-not/alternatives structure the rubric rewards.

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?

No annotations are provided, so the description carries the full burden. It explicitly states 'Safe, read-only validation tool. No file modifications,' which is valuable behavioral disclosure beyond the core purpose. It does not mention network behavior or return format, but the safety profile is clearly communicated.

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 well-organized with clear sections and front-loaded purpose. It is slightly redundant—the first bullet under USAGE GUIDELINES largely restates the main description—but overall it is compact and every major section 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?

For a single-parameter tool, the description covers purpose, usage boundaries, and safety adequately. There is no output schema, and the description does not explicitly describe the return shape, but it is still complete enough for an agent to decide when to invoke this tool and with what target.

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 single parameter 'target' already has a clear description: 'Target live URL or local file path to inspect.' The tool description does not add additional semantic detail beyond that, 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: 'Extracts and validates Schema.org JSON-LD structured data' and enumerates the supported schema types. It clearly distinguishes this audit tool from the other seo_audit_* siblings by focusing on JSON-LD validation rather than content, performance, or technical audits.

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 provided: 'Use to inspect whether structured data is correctly embedded and free of JSON syntax or validation errors.' It also names the alternative tool for fixes: 'Do NOT use to apply schema fixes to files; use seo_generate_code_fix with the jsonLdSchema parameter instead.' This removes ambiguity about when to call this tool versus a 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?

With no annotations provided, the description carries the full burden and does so well. It discloses that the tool is read-only, issues HTTP GET requests, respects robots.txt directives and maxPages limits, and makes no disk modifications. This is strong behavioral transparency for a network-crawling 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?

The definition is well structured and front-loaded: the opening sentence explains scope and outputs, the usage guidelines give clear routing, and the behavioral transparency section is terse yet complete. Every sentence adds distinct 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?

The description covers what the tool does, when to use it, and its safety profile, which is enough for selection and invocation. It mentions it compiles a scorecard and inventory report, but since there is no output schema, slightly more detail about the returned report format would make it fully 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?

Schema description coverage is 100%, so the baseline is 3. The description reinforces that maxPages limits the crawl and that robots.txt is checked, but it does not add substantive parameter meaning beyond the schema's own documentation.

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 (crawls/batch-audits), a clear resource (sitemap.xml or local discovered routes), and distinct operations (robots.txt cross-check, security header audit, site-wide scorecard). It clearly separates this multi-page tool from single-page and sitemap-generation 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?

Usage guidelines are explicit: use for entire websites with multiple pages, do not use for single-page analysis (use seo_generate_full_audit), and do not use for sitemap generation (use seo_generate_sitemap_and_robots). This gives an agent direct routing cues with sibling names.

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?

No annotations are present, so the description carries full behavioral disclosure. It explicitly states 'Safe, read-only diagnostic evaluation', describes network behavior ('Issues HTTP GET requests if given a URL'), and confirms no side effects ('reads local file if given a file path. No disk modifications'). This is exactly the transparency agents need.

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 well-structured with clear labeled sections (USAGE GUIDELINES, BEHAVIORAL TRANSPARENCY) and avoids redundancy. Every sentence adds value: scope, exclusions, alternatives, and runtime behavior are each covered in compact form.

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 absence of annotations and output schema, the description provides strong coverage of purpose, usage, exclusions, and side effects. It does not describe the return format of the audit results, which is a minor gap, but is otherwise complete enough 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?

Schema description coverage is 100%, so the input schema already documents both 'target' and 'projectPath' accurately. The description adds a small behavioral nuance by noting HTTP GET for URLs versus local file reads, but it does not materially enrich parameter 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?

The description opens with a specific verb and resource: 'Performs a Technical SEO audit on a page or URL', then enumerates the exact dimensions checked (canonical, robots meta, sitemap alignment, trailing slash, mixed content, viewport, charset). This clearly distinguishes it from audit tools focused on content, performance, or local SEO.

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 USAGE GUIDELINES section explicitly states what the tool is for ('audit indexing, crawlability, canonicalization') and what it is not for, naming the sibling tools 'seo_audit_onpage', 'seo_audit_sitemap_multipage', and 'seo_generate_full_audit' as alternatives. This provides unambiguous routing 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?

The description explicitly states it is read-only, issues HTTP GET requests for live URLs, and reads local files without modifying them. Since no annotations were provided, this transparency fully covers the behavioral contract and sets accurate expectations for side effects.

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 concise and well-organized: a main action sentence followed by bulleted usage and behavior notes. Every sentence adds value—no filler or redundancy. The most important information (what it does) 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?

Given the absence of an output schema, the description compensates by listing the extracted metadata fields. It also covers usage boundaries and behavioral details, making the tool's capabilities fully understandable for an agent without needing to inspect additional documentation.

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?

Both parameters are described with concrete examples and clarifications. The 'target' parameter explains it can be a URL or file path with format examples; 'pageType' explains it is an optional override with example values and notes that inference occurs when omitted. This adds meaning beyond the raw schema types.

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 crawls a live URL via HTTP or parses a local HTML/template file to extract raw SEO metadata, listing specific data points (title, meta description, headings, etc.). It explicitly differentiates from sibling tools by noting that multi-page crawling and framework discovery are handled by other 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?

It provides explicit when-to-use guidance ('before running specialized audits or when analyzing a single page') and when-not-to-use guidance with named alternatives ('Do NOT use for multi-page batch crawling; use seo_audit_sitemap_multipage' and 'Do NOT use to discover framework architecture; use seo_discover_project'). This leaves no ambiguity.

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 openly states that the tool is safe, read-only, makes no network calls, and modifies no files. This is exactly the kind of behavioral disclosure needed when no annotations are provided.

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 two concise sentences, with usage and behavior clearly separated into distinct sections. There is no redundancy or unnecessary detail, making it easy for an agent to parse quickly.

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 large set of sibling tools, this description effectively differentiates itself by specifying the local-scope use case and explicitly naming alternatives for remote audits. It provides enough context for an agent to select it correctly.

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

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

The single parameter 'projectPath' is fully described in the schema with a clear definition, example values, and a default. While the tool description itself adds no extra detail, the schema coverage is complete and unambiguous, so only a minor deduction is warranted.

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's function: discovering website architecture, frameworks, routing, sitemap/robots, and page inventory. The verb 'discovers' is specific and the resource (website architecture) is well-defined.

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 states when to use ('when starting an audit of a local codebase') and when not to use (remote websites or live URLs), with clear alternative tool names provided. This leaves no ambiguity about the intended use case.

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?

No annotations are provided, so the description carries the behavioral burden. It discloses the most critical trait: the tool is non-destructive by default and only modifies disk when applyDirectly is explicitly true. It also clarifies that the default output is a unified diff preview. A note about error handling or handling of pre-existing tags would be additional value, but the core side-effect behavior is well covered.

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 efficiently organized into overview, usage guidelines, and behavioral transparency sections. Every sentence adds distinct value with no filler or repetition. The most important scoping and safety information is front-loaded, and the bullet-list format makes the guidance easy for an agent to parse.

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 tool with 8 parameters, no output schema, and no annotations, the description covers the essential context: what it fixes, which frameworks it supports, when to use it, and what the default output and side-effect behavior are. It also points to seo_validate_code_fix as the required follow-up. A brief note on behavior when no fixes are generated would push it to a 5, but nothing critical 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 description coverage is 100%, so the parameters are already thoroughly documented in the input schema. The description adds helpful context by naming the categories of fixes and emphasizing framework-awareness, but it does not add parameter-interdependency or syntax details beyond the schema. This meets the baseline-3 expectation for fully covered schemas.

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 action ('Generates framework-aware code fixes') and enumerates the target resources (missing titles, meta descriptions, canonical URLs, JSON-LD schemas, WebMCP discovery links) plus the supported frameworks (Laravel Blade, Next.js, HTML, PHP, Astro, Svelte). It also identifies the unified diff preview output, which sets clear expectations. This clearly distinguishes it from the sibling audit, sitemap, and validation 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?

Explicitly states when to use the tool ('Use after audit tools detect...') and provides a direct exclusion ('Do NOT use for general code refactoring unrelated to metadata, schema, or SEO tags'). It also gives a sequencing instruction to run seo_validate_code_fix immediately after applying changes, which is highly actionable for an agent.

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 provided, the description carries the full burden. It explicitly states 'Safe, read-only comprehensive synthesis' and 'Generates Markdown and JSON reports without modifying files', fully disclosing side effects and safety profile.

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 well-structured: purpose, usage, and behavioral transparency each in a short sentence. No redundancy or 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?

The description lists the audit dimensions and outputs (scores, grades, action matrix, Markdown/JSON reports), giving a solid functional overview. However, without an output schema, it does not specify the structure of the generated reports or the exact composition of the action matrix, which would be valuable for a comprehensive audit 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 coverage is 100% with clear descriptions for both parameters. The description text adds no additional semantic detail beyond the schema, 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?

Clearly states the tool executes a comprehensive 8-dimension audit across specified categories (Technical, On-Page, AEO, GEO, Content, CRO, Performance) and produces scores, grades, and an action matrix. This verb+resource combination differentiates it from single-dimension 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?

Explicitly states when to use (primary single-page audit tool for complete health check) and when not to use (multi-page domain crawls → sitemap_multipage; single dimension → dedicated seo_audit_* tools). Leaves no ambiguity for selection.

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 provided, the description carries the full burden, and it delivers via a dedicated 'BEHAVIORAL TRANSPARENCY' section: 'Safe, read-only strategic synthesis. Produces strategic Markdown plans without modifying any files.' This discloses read-only behavior, output format, and non-modification of files. No contradiction exists since annotations are absent.

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 is front-loaded in the first sentence, followed by compact, clearly delimited USAGE GUIDELINES and BEHAVIORAL TRANSPARENCY sections. Every sentence earns its place with no redundancy or 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?

Given moderate complexity (2 params, no output schema, no annotations), the description covers purpose, usage boundaries against siblings, and behavioral transparency including output format. A minor gap is that it doesn't clarify its relationship to 'seo_generate_full_audit', another synthesizing sibling, though the strategic-marketing angle largely distinguishes it.

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

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

Schema description coverage is 100%, so the baseline is 3. The schema already fully defines both parameters ('target' as URL or file path, 'projectPath' as optional architecture context). The description adds no per-parameter meaning beyond the schema, so it stays at the baseline.

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 ('synthesizes audit findings') and a concrete deliverable ('high-impact digital marketing growth blueprint'), enumerating four explicit outputs (ToFu/MoFu/BoFu intent mapping, CRO levers, AEO tactics, 30-60-90 roadmap). This clearly distinguishes it from the 20 sibling audit, code-fix, and generation 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?

The description explicitly states when to use ('preparing a strategic marketing plan, client proposal, or business growth recommendations based on site audit data') and when not to use, naming two specific alternatives ('seo_generate_code_fix' for code fixes and 'seo_audit_technical' for quick diagnostics). This is model-friendly routing 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?

Without annotations, the description carries the full burden, and it does so well by stating this is a pure generation tool, returns file contents as text, and does not write to disk directly. This is a meaningful disclosure of side effects and output format, though it could also mention failure behavior or permissions if relevant.

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 well-organized into clear sections: a concise main summary, usage guidelines with routing exclusions, and a short behavioral transparency note. Every sentence earns its place and the critical 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?

The tool is simple (3 params, all schema-documented) and the description explicitly states the output format, the side-effect behavior, and when to use alternatives. Even without an output schema, an agent has enough information to invoke it correctly and understand the result.

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 input schema fully explains targetUrl, urls, and disallowedPaths. The description itself does not add parameter-level detail beyond what the schema already provides, so a 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 opens with a specific verb ('Generates') and identifies the exact resources produced ('sitemap.xml and robots.txt files') along with the crawler directives they include. This clearly distinguishes it from the sibling audit tools like seo_audit_robots_and_sitemap.

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 guidelines explicitly state when to use the tool (missing or outdated files, clean configuration needed) and when not to, naming the exact sibling alternatives for audits and crawling. This gives an agent direct routing instructions with no ambiguity.

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?

No annotations are provided, so the description carries the full safety burden. It explicitly says 'Safe, read-only ecosystem analysis. Makes no modifications to codebase or remote sites,' which directly addresses side effects and mutability concerns.

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 well structured: a one-sentence purpose, three scoped bullets for usage, and a one-line behavioral note. Every section adds distinct information with no redundant filler.

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

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

For a complex multi-output tool with no output schema, the description lists what results will be produced (vertical, competitor benchmarks, backlink/directory targets, topic clusters) and gives clear usage boundaries. It stops short of specifying return format or ordering, but invocation is still unambiguous with a single documented parameter.

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%: the only parameter, target, is described as a website codebase directory path. The free-text description adds no additional parameter semantics, so the baseline of 3 applies because the schema already documents the parameter sufficiently.

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 opens with a specific action and resource: 'Analyzes a website' and enumerates concrete deliverables (market vertical, competitor archetypes, backlink/directory targets, keyword topic clusters). This clearly differentiates it from the audit-focused siblings and from seo_generate_code_fix and seo_test_web_mcp.

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?

A dedicated USAGE GUIDELINES section states when to use the tool ('expand organic reach, plan off-page directory submissions, identify competitor benchmarks') and names explicit alternatives for excluded cases: 'seo_generate_code_fix' for on-page code repairs and 'seo_test_web_mcp' for protocol validation.

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 present, the description carries the full burden and meets it: it declares the tool 'safe, read-only', specifies that it makes HTTP GET/HEAD requests to standard discovery endpoints, and states it modifies no files. This gives an agent a clear side-effect profile.

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 well-structured with clear purpose, usage, and behavior sections and no filler. It loses one point only for mild redundancy: the first usage bullet restates the opening purpose, and the behavior section repeats the safe/read-only idea in two adjacent sentences.

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 2-parameter, no-output-schema tool, the description covers what the tool does, when to avoid it, and its safety profile. A small gap is that it does not describe the exact result format, such as how pass/fail findings or generated blueprints are returned.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds useful parameter context beyond the schema: it expands the accepted input to local endpoints and clarifies that the targetLanguage parameter produces copy-paste implementation blueprints across 11 programming languages.

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 begins with a specific verb and resource ('Tests a live website or local endpoint for Web MCP enablement') and lists the exact protocol endpoints and manifests checked. It is clearly distinguishable from the sibling SEO audit tools, and the 'Do NOT use' guidance reinforces that distinction.

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 states when to use the tool ('test if a web application exposes an agent-accessible Model Context Protocol interface') and when not to use it, naming the alternatives 'seo_audit_technical' or 'seo_audit_onpage'. No inference is required.

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

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

With no annotations provided, the description carries the full burden and clearly states the operation is safe, read-only, reads the modified file, performs AST/regex checks, and makes no further modifications. This covers the critical non-mutation trait and adds method detail; it is only slightly limited by not describing the output/return 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?

The purpose statement is front-loaded and the labeled Usage/Behavior sections make the definition scannable. There is minor redundancy in repeating 'modified file' and 'read-only/no modifications,' but the description remains relatively compact for the amount of guidance it provides.

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

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

The definition covers purpose, usage, and safety well, but there is no output schema and the description does not specify return format or where the 'Before' score comes from. For a tool whose whole point is Before/After scores, this leaves some ambiguity; still, an agent can correctly invoke it with a file path and the provided timing guidance.

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 the filePath parameter already has a clear schema description, so the baseline is 3. The description reinforces that the path should point to a modified file, but it does not add parameter-specific syntax, path format, or optional-parameter guidance beyond what the schema provides.

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 ('Validates') with a defined resource ('modified source files') and enumerates concrete checks: syntax errors, duplicate meta/title tags, broken JSON-LD, and Before/After SEO score improvements. This clearly distinguishes it from the audit siblings, which are for unedited or standalone analysis.

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 usage section explicitly states when to use the tool (immediately after seo_generate_code_fix), and it explicitly says when not to use it (standalone audit on unedited files) while naming alternatives (seo_audit_onpage, seo_generate_full_audit). This is model behavior for routing an agent to the correct sibling.

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