Scores a website's online presence 0-100 and lists the top issues to fix. English/Arabic.
Scored across 2 tools
The two tools are explicitly complementary: scan_website starts a live scan and creates a lead, while get_scan_result only reads an existing scanId and never starts a scan. The descriptions state this read-vs-start boundary outright, so there is no realistic way to misselect.
Both names follow a clean snake_case verb_noun pattern (scan_website, get_scan_result) and use the same domain vocabulary (scan/scanId). No mixed casing or competing verb styles.
Two tools is thin in absolute terms but exactly the minimal pair needed for an async start-then-poll workflow. Nothing is padded or redundant, though a couple more lifecycle tools could be justified.
The core lifecycle (start scan, retrieve result after processing) is fully covered, including documented failure/expiry behavior. Minor gaps exist: no cancel-a-scan, no list/status-of-my-scans, and no way to re-fetch a report beyond the 7-day scanId window.
Collect the result of a scan that scan_website started but had not finished when it answered. Call scan_website first; if its status is "processing", wait a little (about 30 seconds) and call this with the scanId it returned. Returns the same result as scan_website: "processing" (ask again shortly), "ready" (the 0-100 score and top issues) or "failed". It only reads: it never starts a scan. A scanId stops working 7 days after it was issued.
| Name | Required | Description | Default |
|---|---|---|---|
| scanId | Yes | The scanId that scan_website returned with status "processing". | |
| waitSeconds | No | Optional: how many seconds to wait for a scan that is still running before answering (0-20, default 0 = answer now). |
| Name | Required | Description |
|---|---|---|
| note | Yes | Plain-language context about the score and the full report to come. |
| score | Yes | 0-100 online-presence score, or null until the quick pass finishes. |
| scanId | No | Present while status is "processing": pass it to get_scan_result to collect the finished result. |
| status | Yes | "ready" = quick score below; "processing" = still running, report follows; "failed" = site could not be checked. |
| website | Yes | The website that was scanned. |
| findings | Yes | The top issues to fix first, most urgent first. |
| Yes | A WhatsApp link to reach the Kashif team about this business. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnly/idempotent/non-destructive, and the description adds behavior beyond them: it never starts a scan, it returns the same payload as scan_website, and scanIds expire 7 days after issuance. The expiry/retry semantics are exactly the kind of operational context an agent cannot infer from structured fields.
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 the core purpose, then prerequisites, then return states, then the two key constraints. Four sentences with no filler; each one changes how the agent behaves.
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?
Complete for a continuation tool: an output schema exists so return values need no elaboration, annotations carry the safety profile, and the description closes the remaining gaps (ordering, timing, expiry, idempotent re-polling).
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 real meaning: scanId comes from scan_website's "processing" response and stops working after 7 days, and it clarifies that retries are expected rather than error conditions. The ~30 second guidance sits slightly at odds with waitSeconds' 20-second cap, but does not obscure the parameter's purpose.
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 ("collect the result of a scan") and immediately scopes it against the sibling: it is the continuation of scan_website, not a scan starter. An agent can distinguish it from scan_website 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?
Explicitly sequences the workflow: call scan_website first, and only call this when its status is "processing". It also prescribes the retry cadence (~30 seconds) and interprets each returned state ("processing", "ready", "failed") into a next action.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Score how well a business shows up online, out of 100, and name what is hurting it most. Give it a website (and an email to send the full report to) and it runs Kashif's audit of the business's online presence: whether customers can find them in search, whether AI assistants can read and recommend them, how fast the site feels on a phone and the first impression it makes, how trustworthy it looks, and how easy the business is to reach (WhatsApp, phone, a contact form). Returns a 0-100 score with the top issues to fix first. Use it whenever someone asks to audit, check, review, grade or improve a company's website or online presence. This starts a live scan and creates a lead for the Kashif team, who follow up with the full written report by email. If the result comes back with status "processing", the scan is still running: wait about 30 seconds, then call get_scan_result with the scanId it returned to collect the score.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The business’s website, e.g. example.com or https://example.com. | |
| name | No | Optional: the person or business name, used to label the lead. | |
| Yes | An email address to send the full written report to. Required — this is a lead for the team. | ||
| language | No | Report language: "en" (default) or "ar" for Arabic. |
| Name | Required | Description |
|---|---|---|
| note | Yes | Plain-language context about the score and the full report to come. |
| score | Yes | 0-100 online-presence score, or null until the quick pass finishes. |
| scanId | No | Present while status is "processing": pass it to get_scan_result to collect the finished result. |
| status | Yes | "ready" = quick score below; "processing" = still running, report follows; "failed" = site could not be checked. |
| website | Yes | The website that was scanned. |
| findings | Yes | The top issues to fix first, most urgent first. |
| Yes | A WhatsApp link to reach the Kashif team about this business. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations, the description discloses critical side effects: it starts a live scan, creates a lead for the Kashif team, and triggers a follow-up written report by email. It also explains the async processing path and required wait before retrieving results. This is exactly the behavioral context an agent needs before invoking a non-read-only, open-world 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 description is front-loaded with the core purpose, score range, and return meaning. It is somewhat dense and repeats the 0-100 score concept, but every sentence carries useful selection, side-effect, or async-handling information. Minor compression could improve it, but it is not bloated.
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 complexity, the description covers purpose, usage conditions, required inputs, side effects, lead creation, email follow-up, and async result collection. An output schema exists, so the description need not explain return formatting in detail, but it still clarifies the 0-100 score and top issues. Nothing essential for 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 coverage is 100%, so the schema already documents all parameters, establishing a baseline of 3. The description adds useful semantics by explaining that the URL is the business website and the email is required because it sends the full report and creates a lead. It does not add details for name or language, but the schema covers those adequately.
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: it scores a business's online presence out of 100 and names top issues. It also distinguishes itself from the async sibling by explaining that a processing result should be collected with get_scan_result. An agent can select it without opening the 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?
It gives explicit usage triggers: 'whenever someone asks to audit, check, review, grade or improve a company's website or online presence.' It also handles the async edge case by naming get_scan_result and specifying a ~30-second wait. Alternative routing is clear.
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_scan_resultscan_website1 field changedOutput schema / properties / scanIdAdded value: +{
+ "description": "Present while status is \"processing\": pass it to get_scan_result to collect the finished result.",
+ "type": "string"
+}scan_websiteScores a website's online presence 0-100 and lists the top issues to fix. English/Arabic.
Free website score for speed, SEO, security and AI search readiness, with the fixes.
Public website health scan, AI-crawler and structured-data readiness, and a local presence score.
Grade any website out of 100 for speed, SEO, trust and lead capture, with plain-English fixes.
Add one secure layer between your agents and this server.