Free GEO score of a web page or text: how easily AI assistants can quote it, with fixes. No key.
Scored across 2 tools
The two tools are clearly distinguished by input type: score_text accepts text directly, while score_url fetches and scores a URL. Their descriptions explicitly state the difference and even recommend using score_text when a URL cannot be fetched, leaving no ambiguity about which tool to use.
Both tools follow the same consistent verb_noun pattern in snake_case: 'score_text' and 'score_url'. The naming is predictable and immediately conveys the action and the resource type.
With only two tools, the server covers the two possible ways to provide content (raw text or a URL) for scoring. This is exactly the right scope for a single-purpose GEO scoring service, with no redundant or missing tools.
The server's purpose is narrowly defined as computing a GEO score for content, and the two tools cover both text and URL inputs completely. They return overall score, criteria breakdowns, fixes, and a link, leaving no obvious gaps for the stated domain.
Compute the GEO score of a text with Citead: an article draft, a page copy, markdown, plain text or HTML. Returns the overall score (0 to 100), the score of five criteria (AI citability, naturalness, authority and citations, semantic richness, content organization), the main fixes to apply, and a link to Citead's free live editor. The GEO score (0 to 100) measures how easy the content is for a language model to understand, reuse and cite: information density, quotable sentences, self-contained paragraphs, sourced and dated facts, clear structure, freshness. Naturalness is returned as a criterion but does not count in the score. It is computed by deterministic rules, without a language model: the same content always gets the same score. It does not guarantee that an AI assistant will cite the page. Free, no API key, the text is not stored. Texts under 300 words get a capped score (at most 65).
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | Page title. Defaults to the first heading. | |
| content | Yes | The text to score: markdown, plain text or HTML. | |
| language | No | Language of the text. Omit to detect it. Only English and French have dedicated rules; other languages use the English ones. |
| Name | Required | Description |
|---|---|---|
| url | No | |
| title | No | |
| criteria | Yes | Score of each of the five criteria, 0 to 100. The overall score is computed from sub-signals of four of these criteria plus freshness, with caps for very short content, so it is not their plain average. Naturalness does not count in the overall score. |
| geo_score | Yes | Overall GEO score, 0 to 100. |
| top_fixes | Yes | Main corrections, most important first. |
| word_count | Yes | |
| details_url | Yes | Citead page with the full breakdown. Give it to the user. |
| score_meaning | Yes | |
| remaining_quota | Yes | Free scores left for this IP address in the current windows. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the annotations (readOnly/idempotent/destructive=false) by disclosing that scoring is deterministic with no LLM, that identical content always yields the same score, that text is not stored, that no API key is needed, that short texts (<300 words) are capped at 65, that naturalness is excluded from the total, and that citation is not guaranteed. These are exactly the behavioral traits an agent must know before calling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with purpose and inputs, then caveats. It is dense and every sentence carries information, though enumerating the return fields in detail is somewhat redundant given an output schema exists. Still efficient overall.
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 an output schema covering return values, the description still supplies the critical edge cases an agent needs: score scale and criteria breakdown, the short-text cap, the naturalness exclusion, and the no-guarantee caveat. Nothing essential to correct invocation is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents title, content and language fully (including the language enum and detection fallback). The description adds no parameter-level detail beyond the schema, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource ('Compute the GEO score of a text') and immediately enumerates accepted input forms (article draft, page copy, markdown, plain text, HTML), which implicitly separates it from the sibling score_url that operates on URLs. It also defines the GEO score's meaning, so an agent knows exactly what is being computed.
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 establishes the input scope but never explicitly tells the agent when to choose this over score_url or when not to use it (e.g., for URLs vs raw text). Usage is inferable from the 'text' framing but no routing guidance or exclusions are stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch a public web page and compute its GEO score with Citead. Returns the overall score (0 to 100), the score of five criteria (AI citability, naturalness, authority and citations, semantic richness, content organization), the main fixes to apply, and a citead.com link with the full breakdown. The GEO score (0 to 100) measures how easy the content is for a language model to understand, reuse and cite: information density, quotable sentences, self-contained paragraphs, sourced and dated facts, clear structure, freshness. Naturalness is returned as a criterion but does not count in the score. It is computed by deterministic rules, without a language model: the same content always gets the same score. It does not guarantee that an AI assistant will cite the page. Free, no API key, nothing is stored. Pages behind a login or rendered only by JavaScript may not be fetchable: use score_text with the page text instead.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public http(s) URL of the page to score. |
| Name | Required | Description |
|---|---|---|
| url | No | |
| title | No | |
| criteria | Yes | Score of each of the five criteria, 0 to 100. The overall score is computed from sub-signals of four of these criteria plus freshness, with caps for very short content, so it is not their plain average. Naturalness does not count in the overall score. |
| geo_score | Yes | Overall GEO score, 0 to 100. |
| top_fixes | Yes | Main corrections, most important first. |
| word_count | Yes | |
| details_url | Yes | Citead page with the full breakdown. Give it to the user. |
| score_meaning | Yes | |
| remaining_quota | Yes | Free scores left for this IP address in the current windows. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), but the description adds substantial behavioral context: deterministic rule-based scoring with no LLM, same input yields same score, naturalness is returned but excluded from the total, and no guarantee of actual AI citation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with purpose and return shape, then caveats and the alternative. Dense but every sentence carries information; the criteria enumeration and elaborated GEO definition are slightly verbose but relevant to interpreting the score.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Even though an output schema exists, the description explains what the score means, how it is computed, its limitations, and the fallback path. Nothing an agent needs to select and invoke this tool correctly is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter at 100% schema coverage, so the schema already documents the URL and its constraints. The description adds no format or syntax detail beyond confirming it fetches a public page, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Opens with a specific verb+resource ('Fetch a public web page and compute its GEO score') and immediately defines the score semantics. It distinguishes itself from the sibling by naming score_text as the fallback for login/JS-only pages.
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 the condition under which to use the alternative ('Pages behind a login or rendered only by JavaScript may not be fetchable: use score_text with the page text instead'). Also clarifies cost/auth/storage expectations (free, no API key, nothing stored).
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.
score_textscore_urlGEO scores and content-rewrite suggestions for any web page, as MCP tools.
AI visibility for ChatGPT/Perplexity/Claude — triple score (AEO+GEO+Agent) with fix code. Free.
Checks whether a website is readable and citable by AI systems (ChatGPT, Claude, Perplexity, etc.)
Free AI visibility (GEO/AEO) audit: can ChatGPT, Claude and Perplexity find and cite your website?
Add one secure layer between your agents and this server.
