SEO and AI-search audit for websites, built for Uzbekistan (Uzbek and Russian sites). Checks on-page SEO, technical health (HTTPS, TLS 1.3, HSTS, HTTP/2-3, robots.txt, sitemap, broken links), AI-search readiness (GEO/AEO), speed and Core Web Vitals, content and social tags, and returns concrete fixes plus AI recommendations for title, description and H1 based on real search demand in Uzbekistan. Start an audit with start_audit, then fetch the result with get_audit.
Scored across 2 tools
The two tools are cleanly separated: start_audit initiates the audit and returns an ID, while get_audit retrieves results by that ID. There is no overlap in purpose, and the async polling pattern is explained clearly.
Both tools follow a consistent verb_noun snake_case pattern (start_audit, get_audit) and share the same '_audit' resource suffix. Naming is fully predictable.
Two tools is on the thin side, but it reflects a minimal start-then-poll design. It covers the immediate need but offers no breadth beyond a single audit workflow.
The start/poll pair forms a complete create-and-read lifecycle for a single audit, with caching and rate-limit behavior documented. Minor gaps exist (no listing of past audits, no cancel/delete), but core usage is not blocked.
Returns the result of a gizz.uz SEO audit: overall score and grade, category scores, failed/warning checks with concrete advice, broken links, AI recommendations for title/description/H1 and content, top search queries with monthly volume in Uzbekistan, and links to the full report and PDF. If the audit is still running, status is not "done" — call again in a few seconds.
| Name | Required | Description | Default |
|---|---|---|---|
| detail | No | "summary" (default) returns only failed and warning checks; "full" also lists every passed check. | summary |
| audit_id | Yes | Audit id (8 characters, e.g. "V47WN2Ya") or a gizz.uz report link (https://gizz.uz/sayt-audit/natija/… or https://gizz.uz/ru/audit-sajta/rezultat/…). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description earns credit for adding asynchronous-job semantics: a status field that may not be "done" and a retry cadence. It does not mention rate limits or auth requirements, so it stops short of a 5.
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-loads the purpose and the bulk of the content is a useful enumeration of return fields rather than padding. The polling note is correctly placed last, though the content list is a single very long clause chain that could be tightened.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description carries the full burden of telling the agent what comes back — and it does so item by item, plus the async status/polling behavior. For a 2-param, no-output-schema tool this is complete enough to call correctly without further investigation.
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%: audit_id format and the summary/full enum are both fully documented in the schema, so the baseline is 3. The description alludes to the failed/warning checks that the summary mode returns but never maps that to the detail parameter or adds format detail 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?
Opens with a specific verb and resource ("Returns the result of a gizz.uz SEO audit") and then enumerates exactly what the payload contains — score/grade, category scores, failed checks, broken links, AI recommendations, queries, report links. An agent can distinguish this from the sibling start_audit (which initiates, this retrieves) 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 concrete polling guidance: if the audit is still running, status is not "done", so call again in a few seconds. That tells the agent the using-context (after start_audit, possibly repeatedly) but never explicitly names the alternative sibling or states when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Starts a free gizz.uz SEO audit of a web page and returns its audit_id. No API key needed: 3 new audits per day per client address (resets at 00:00 Tashkent, UTC+5). A page audited in the last 24 hours is returned from cache without using the limit, and a page already being audited is not started twice. The audit runs in the background: call get_audit with the audit_id until status is "done".
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public page to audit, e.g. "https://example.uz" or "example.uz/page". | |
| language | No | Language of the report texts: "uz" (Uzbek, default) or "ru" (Russian). | uz |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds substantial context beyond the annotations: free/no API key, a hard daily rate limit with reset timezone, cache short-circuiting, dedupe of in-progress audits, and asynchronous background execution with a polling contract. These are exactly the traits an agent needs to avoid misusing the tool, and none are derivable from readOnlyHint/idempotentHint/destructiveHint/openWorldHint.
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?
Four dense sentences, front-loaded with the purpose and return value, followed by constraints and the polling instruction. Every sentence carries information the agent needs; no 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?
No output schema exists, but the description compensates by naming the returned audit_id and the full async lifecycle via get_audit. Combined with fully documented parameters and rich operational constraints, an agent has everything needed to call and follow up 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% and both parameters (url, language with enum) are already documented, so the agent loses nothing by the description not restating them. The description adds no format or constraint 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 ("Starts a free gizz.uz SEO audit of a web page") and names the return value (audit_id). It implicitly separates itself from the sibling get_audit by making start vs. poll explicit in the last sentence.
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 concrete context for when the limit applies (3/day per client address, resets 00:00 Tashkent), when the cache bypasses the limit (page audited in last 24 hours), and the required follow-up workflow (poll get_audit until status is "done"). No explicit when-not-to-use or named alternative beyond get_audit, so not a 5.
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.
get_auditstart_audit
Add one secure layer between your agents and this server.