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 have clearly distinct purposes: score_text operates on provided text, while score_url fetches and scores a public web page. Their descriptions explicitly clarify the difference and even advise using score_text when a URL cannot be fetched.
Both tools follow the same consistent pattern: score_ followed by the input type (text, url). No mixing of conventions or vague verbs.
The server's purpose is narrow—computing GEO scores—and two tools perfectly cover the two input modalities (text and URL). No unnecessary tools, no missing input method.
The tool surface fully covers the stated domain: scoring text and scoring a URL. There are no obvious missing operations for a stateless scoring service, and the descriptions handle edge cases like JS-rendered pages by directing users to score_text.
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 each criterion (semantic richness, AI citability, freshness, content organization, authority and citations, and naturalness, which does not count in the score), 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 criterion, 0 to 100, in this order: semantic richness, AI citability, freshness, content organization, authority and citations, and naturalness, which does not count in the score. The overall score is computed from sub-signals of the first five, with caps for very short content, so it is not their plain average. |
| 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 that shows this analysis again, without publishing it to the public leaderboard. 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?
Despite annotations covering read-only and idempotent behavior, the description adds rich context beyond them: deterministic rule-based computation, no storage, no API key, capped score for short texts, and what the score does not guarantee. This is exactly the extra behavioral detail that helps an agent set expectations.
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 informative but somewhat repetitive: it describes the return values and then re-explains the GEO score and naturalness. It could be tightened, and the most critical constraints are not front-loaded. Still readable and not excessively long.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given a read-only scoring tool with an output schema, the description is complete. It explains what is returned, the scoring dimensions, the deterministic nature, the short-text cap, and privacy. No essential information is missing for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all three parameters including defaults and constraints. The description adds the accepted formats but doesn't provide additional meaning beyond the schema. 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 states a specific verb and resource ('Compute the GEO score of a text with Citead') and lists accepted formats. It clearly conveys purpose. It doesn't explicitly differentiate from the sibling tool 'score_url', but the name and description make the distinction obvious.
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 'Compute the GEO score of a text' and the accepted input formats. However, there is no explicit guidance on when to use this vs the sibling score_url or any alternatives/exclusions. It's adequate but leaves the agent to infer the scenario.
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 each criterion (semantic richness, AI citability, freshness, content organization, authority and citations, and naturalness, which does not count in the score), the main fixes to apply, and a citead.com link that shows the analysis again. 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. Citead does not store the page content or its score; it keeps only daily counts of outcomes, the domain name of sites that block its fetcher (45 days) and per-IP rate-limit counters. The details_url page does not publish the result to the public leaderboard. 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 criterion, 0 to 100, in this order: semantic richness, AI citability, freshness, content organization, authority and citations, and naturalness, which does not count in the score. The overall score is computed from sub-signals of the first five, with caps for very short content, so it is not their plain average. |
| 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 that shows this analysis again, without publishing it to the public leaderboard. 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 declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: deterministic rule-based scoring (same content = same score), no LLM involved, no guarantee of citation, no API key, per-IP rate limiting, and exactly what Citead retains (daily outcome counts, blocked-domain names for 45 days, IP counters).
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?
Well front-loaded: fetch action, then return values, then scoring explanation, then constraints. It is long, and the naturalness caveat is stated twice ('naturalness, which does not count in the score' and again 'Naturalness is returned as a criterion but does not count in the score'), which is minor waste.
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?
An output schema exists so return values need not be explained, yet the description still enumerates the criteria and fixes clearly. Combined with privacy, rate-limit, fetchability limits, and the sibling escape hatch, an agent has everything needed to call this correctly and interpret 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% and there is a single required parameter already documented as 'Public http(s) URL of the page to score.' The description reinforces that the URL must be public and fetchable but adds no format, length, or syntax detail beyond the schema. 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?
Opens with a concrete verb+resource: 'Fetch a public web page and compute its GEO score with Citead.' It also distinguishes itself from its only sibling by stating that login-protected or JS-rendered pages should go to score_text instead, so an agent can route without opening either 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?
Gives an explicit use condition (public http(s) URL) and an explicit exclusion with the named alternative: pages behind a login or rendered only by JavaScript should use score_text with the page text. The 'free, no API key' note further clarifies the calling context.
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_text2 fields changedOutput schema / properties / criteria / descriptionPrevious value: -"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."New value: +"Score of each criterion, 0 to 100, in this order: semantic richness, AI citability, freshness, content organization, authority and citations, and naturalness, which does not count in the score. The overall score is computed from sub-signals of the first five, with caps for very short content, so it is not their plain average."Output schema / properties / details_url / descriptionPrevious value: -"Citead page with the full breakdown. Give it to the user."New value: +"Citead page that shows this analysis again, without publishing it to the public leaderboard. Give it to the user."score_url2 fields changedOutput schema / properties / criteria / descriptionPrevious value: -"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."New value: +"Score of each criterion, 0 to 100, in this order: semantic richness, AI citability, freshness, content organization, authority and citations, and naturalness, which does not count in the score. The overall score is computed from sub-signals of the first five, with caps for very short content, so it is not their plain average."Output schema / properties / details_url / descriptionPrevious value: -"Citead page with the full breakdown. Give it to the user."New value: +"Citead page that shows this analysis again, without publishing it to the public leaderboard. Give it to the user."score_textscore_urlScores whether AI assistants can read, understand and quote a public website. No account.
Free SEO/GEO audits of public websites and AI answer-engine citation checks. No login or API key.
GEO scores and content-rewrite suggestions for any web page, as MCP tools.
Free AI visibility and GEO audit: see what AI reads on your site and whether its answers cite you.
Add one secure layer between your agents and this server.
