Generate SEO structured data: JSON-LD schema, robots.txt, sitemaps, hreflang, Open Graph, meta.
Scored across 9 tools
run_marsgeo_tool duplicates seven of the eight specific tools (faq-schema, product-schema, robots-txt, sitemap, hreflang, meta-description, open-graph generators), so an agent cannot easily tell whether to call the dedicated tool or the dispatcher. The remaining dedicated tools are individually distinct, but the catch-all creates substantial overlapping boundaries.
Seven tools follow a clean generate_<artifact> verb_noun pattern, and validate_json_ld fits the verb_noun convention. Only run_marsgeo_tool deviates by embedding the server name and using a generic verb, a minor inconsistency.
Nine tools is well-scoped for an SEO generation/validation server, and each dedicated tool covers a discrete output artifact. The single catch-all tool is the only redundancy rather than a count problem.
Core SEO artifacts (schema, robots.txt, sitemap, hreflang, meta description, OG tags, JSON-LD validation) are covered, and run_marsgeo_tool hints at extractors, previews, and analyzers. Several of those capabilities are reachable only through the dispatcher with no dedicated tool, a minor gap.
Generate FAQPage JSON-LD structured data from question/answer pairs.
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It doesn't say whether the output is returned as a string, written to a file, or injected into a page, nor whether it validates the generated markup or has side effects. For a generator tool with zero structured disclosure, this is a real gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One well-formed sentence, front-loaded with the verb and resource, and every word earns its place. It is terse, which is fine for the conciseness dimension even though other dimensions suffer from the thinness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No annotations, no output schema, 0% parameter description coverage, and an undocumented nested item shape leave the agent guessing about the return value, error behavior, and input constraints. The description would need to do far more work here.
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 is an array whose item properties are cryptically named 'q' and 'a' with 0% schema description coverage. The description's 'question/answer pairs' does clarify those abbreviations, adding genuine meaning, but it says nothing about array size, ordering, or content constraints.
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 (generate), a specific resource (FAQPage JSON-LD structured data), and the input form (question/answer pairs). The named resource clearly separates it from siblings like generate_product_schema or generate_open_graph, though it never explicitly says so.
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 phrase 'from question/answer pairs' implies the trigger condition (you have FAQ content and need structured data), but there is no statement of when to prefer this over validate_json_ld or the other generate_* siblings, and no prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate reciprocal hreflang tags for a multilingual site.
| Name | Required | Description | Default |
|---|---|---|---|
| entries | No | ||
| defaultUrl | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries the full behavioral burden. It never says what the output looks like (HTML link tags? JSON-LD?), whether entries must form a complete reciprocal set, or what defaultUrl does when omitted. For a generator tool with zero annotation coverage this is a real gap.
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?
A single tight sentence with the key qualifier front-loaded. No waste, though at this size it may be too terse to be sufficient.
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?
A 2-param generator with no annotations, no output schema, and 0% param coverage needs more: expected output format, reciprocity requirements across entries, and defaultUrl behavior are all 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 0% and neither parameter is explained in the description. 'reciprocal' is the only semantic hint about how entries must relate, but the roles of entries vs. defaultUrl and the meaning of the lang/url fields are undocumented in both places.
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+resource (generate hreflang tags) and adds a meaningful qualifier ('reciprocal', 'multilingual site') that distinguishes it from generic schema generators. Sibling tools are all generators of different artifacts, so the resource name alone is enough to differentiate.
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?
No indication of when to use this vs. alternatives, no prerequisites, no mention of what input is needed. The 'reciprocal' hint implies entries should cross-link, but this is never stated as a usage condition.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Trim and format a paragraph into a meta description within length limits.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes |
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 mentions trimming and formatting within length limits, which is some behavioral information, but doesn't disclose what the length limit is, what happens if the text exceeds it, whether truncation or rejection occurs, or what the output format looks like.
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?
A single efficient sentence with no wasted words. It front-loads the core action ('Trim and format') and the output target ('meta description'). However, its brevity comes at the cost of missing important details.
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 no annotations, no output schema, and 0% schema description coverage, the description is insufficient. It doesn't explain the length limit value, the output format, or how it handles edge cases. An agent would need to experiment to use 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 0% and there is 1 parameter with no description. The description mentions 'a paragraph' as input but doesn't clarify the parameter's expected format, length constraints, or whether it should be plain text or HTML. With low schema coverage, the description must compensate but only minimally does so.
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 clear verb+resource: 'Trim and format a paragraph into a meta description.' This distinguishes it from SEO siblings like generate_sitemap or generate_open_graph. The only gap is that it doesn't differentiate itself from other content-formatting tools, but none of the listed siblings compete for this purpose.
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?
No when-to-use guidance, no prerequisites, and no alternatives mentioned. The description implies the tool operates on a paragraph but doesn't say when to invoke it or when not to. An agent must infer the use case from the name and description alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate Open Graph social-preview meta tags.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | ||
| type | No | ||
| image | No | ||
| title | Yes | ||
| description | No |
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 does not say what form the output takes (raw HTML meta tags, a JSON object, a snippet), whether the tags are meant to be inserted into a page head, or whether any of the optional fields fall back to defaults when omitted.
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?
A single short sentence with no filler, so it is structurally clean and front-loaded. But the brevity here reflects under-specification rather than economy, leaving no room for any of the context an agent needs.
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 five parameters, no annotations, and no output schema, the description is the only place behavioral and parameter context could live, and it supplies almost none. An agent can guess the intent but not the invocation details or the return format.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% across five parameters, and the description adds nothing about them. The names map loosely onto og:title/og:description/og:image/og:url/og:type, but the `type` parameter has no documented enum of standard OG values, and the required-only `title` constraint is never explained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Names a specific verb (Generate) and resource (Open Graph social-preview meta tags), so the purpose is unambiguous. However, it offers no differentiation from siblings like generate_product_schema or generate_meta_description, which also emit markup, so the agent must infer the boundary from the name alone.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no when-to-use guidance, no prerequisites, and no mention of alternatives. With eight siblings in the same generation family, the description never tells the agent when Open Graph tags are the right choice versus a product schema or a meta description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate Product JSON-LD structured data.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| brand | No | ||
| image | No | ||
| price | Yes | ||
| currency | No | ||
| availability | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden and delivers almost nothing: no mention of output format details, whether it writes a file or returns a string, validation behavior, or error handling. It only restates that JSON-LD is produced, which is already implied by the name.
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?
A single short sentence with no padding, so it is concise and front-loaded. But the brevity stems from under-specification rather than disciplined editing, so it does not earn a high mark.
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 6-parameter tool with zero annotation coverage, no output schema, and no parameter documentation, the description is too thin. An agent cannot tell what the tool returns or how to fill the optional fields 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 0% across 6 parameters, and the description adds no parameter meaning whatsoever. The agent gets no guidance on formats for price/currency, enum-like values for availability, or which optional fields matter.
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 ('Generate') and resource ('Product JSON-LD structured data'), which is clear on its own and distinguishable by name from sibling generators like generate_faq_schema. However, it offers no explicit differentiation from validate_json_ld or the other generate_* tools beyond the word 'Product'.
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?
No indication of when to use this tool versus alternatives such as validate_json_ld or generate_open_graph, nor any prerequisites. Usage must be entirely inferred from the tool name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a robots.txt file with allow/disallow rules and an optional sitemap.
| Name | Required | Description | Default |
|---|---|---|---|
| allow | No | ||
| sitemap | No | ||
| disallow | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full behavioral burden. It does not say whether the file is written to disk or returned as text, whether it overwrites an existing robots.txt, whether permission or a target domain is required, or what the output looks like.
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?
A single tight sentence with the core action front-loaded. Nothing is wasted, though its brevity is partly the cause of the gaps elsewhere rather than a virtue earned.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no annotations, no output schema, and 0% schema description coverage, this tool needs the description to explain behavior and parameter formats. It names the fields but omits output form, side effects, and required context, leaving an agent under-informed for a file-generating tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It does marginally by naming the three concepts (allow, disallow, sitemap), but adds no format detail — e.g., that allow/disallow are arrays of path strings or that sitemap is a URL — leaving semantics largely to the bare 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 states a specific verb (Generate) and resource (robots.txt file) plus its contents (allow/disallow rules, optional sitemap). The resource is distinct enough from siblings like generate_sitemap and generate_hreflang, though no explicit sibling differentiation is offered.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool, when not to, or how it relates to the sibling generate_sitemap tool (which is directly relevant given the sitemap parameter). Only the phrase 'optional sitemap' hints at configuration, not usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate an XML sitemap from a list of URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full behavioral burden. It doesn't disclose output format details (whether the XML is returned as a string, file, or URL), URL count limits, or whether URLs are validated/normalized.
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?
A single efficient sentence, front-loaded with the action and artifact. No wasted words.
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 generator with no annotations, no output schema, and a 0%-covered parameter, the description is too thin. It omits return format and input constraints an agent needs to invoke 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?
Schema coverage is 0% with one required array parameter. The description says 'list of URLs' but adds nothing about URL format requirements, absolute vs relative paths, or ordering effects.
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 (Generate) and resource (XML sitemap) plus input source (list of URLs). Compared to siblings like generate_robots_txt or generate_hreflang, the output artifact 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?
Usage is implied by the name and description, but there is no explicit when-to-use guidance or differentiation from sibling generators (e.g., when to use generate_sitemap vs validate_json_ld). Adequate but leaves routing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run any MarsGeo SEO tool by slug. Supported: faq-schema-generator, article-schema-generator, product-schema-generator, how-to-schema-generator, breadcrumb-schema-generator, organization-schema-generator, robots-txt-generator, sitemap-generator, hreflang-generator, meta-description-generator, open-graph-generator, serp-snippet-preview, keyword-density-analyzer, schema-validator, meta-tag-extractor, heading-extractor, json-ld-extractor.
| Name | Required | Description | Default |
|---|---|---|---|
| tool | Yes | ||
| input | No |
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 and delivers little: nothing about invalid-slug handling, whether the underlying tools are read-only or mutate anything, error semantics, or rate limits. The passthrough 'input' object's behavior is likewise undisclosed.
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 first sentence front-loads the dispatch purpose, and the slug enumeration is necessary given the schema has no enum constraint. It is dense and earns its length, though the flat comma list could be grouped by category for faster scanning.
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 generic dispatcher wrapping 16 heterogeneous tools with a free-form nested input object, no output schema and no annotations, the description omits how 'input' should be shaped per tool, what comes back, and how failures surface. An agent can identify the tool but cannot confidently invoke 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 coverage is 0% and the 'tool' property is a bare string, so the description's enumerated slug list is genuinely valuable and compensates for that gap. However, the nested 'input' object (additionalProperties: true) is left entirely unexplained, so half the surface remains undocumented.
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 ('Run') and resource ('any MarsGeo SEO tool by slug') and enumerates the 16 supported slugs, so an agent knows exactly what dispatch surface this covers. It stops short of distinguishing itself from the eight sibling generate_* tools, which overlap almost one-for-one with the listed slugs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no statement of when to use this generic dispatcher versus the dedicated siblings (generate_faq_schema, generate_sitemap, validate_json_ld, etc.). The slug list implies capability but leaves the routing decision entirely to inference, which is costly given eight near-duplicate alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Validate JSON-LD and return the pretty-printed block plus detected @type.
| Name | Required | Description | Default |
|---|---|---|---|
| json | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It discloses the successful return shape (pretty-printed block, detected @type) but says nothing about failure behavior — whether invalid JSON-LD raises an error, returns warnings, or still pretty-prints — which is the core concern for a validation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, front-loaded with the verb and resource, and every clause earns its place by adding the return payload. Nothing is padded.
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 validator with no output schema and an undocumented input parameter, the description omits the two things an agent most needs: the accepted input form and the behavior on invalid input. What it does say about the success return is accurate but thin.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% for the single 'json' parameter, so the description must compensate and does not. It never clarifies whether the input is a raw JSON-LD string, a file path, or a URL, nor any expected format constraints.
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 (Validate) and resource (JSON-LD) and adds what the caller gets back (pretty-printed block plus detected @type). This inherently separates it from the generate_* siblings, though no sibling is named explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no indication of when to call this versus the generate_* tools, no prerequisites, and no mention of what the caller should do with the result. Usage must be inferred entirely from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
generate_faq_schemagenerate_hreflanggenerate_meta_descriptiongenerate_open_graphgenerate_product_schemagenerate_robots_txtgenerate_sitemaprun_marsgeo_toolvalidate_json_ldAudit a page for search and AI answer engines; generate robots.txt, sitemap, head, llms.txt.
One-call audit: robots.txt AI-bot rules, llms.txt, JSON-LD, meta tags, sitemap. Score plus fixes.
Generate 18 AI readiness files (llms.txt, ai.txt, RAG indexes, schema) for any website.
Full-cycle SEO automation for AI agents: technical audits, SEO articles, machine-readable pricing.
Add one secure layer between your agents and this server.
