Grade any website out of 100 for speed, SEO, trust and lead capture, with plain-English fixes.
Scored across 2 tools
The two tools serve completely distinct purposes: one performs an automated audit, the other sends a lead/help request to a human team. Descriptions make the boundary explicit with clear usage triggers.
Both follow a verb_noun pattern (audit_website, request_help), though the noun styles differ slightly (resource vs. action outcome). Still mostly consistent and readable.
Only 2 tools, which feels thin for a grading service; one core audit plus one lead-capture tool leaves little room for filtering, comparison, or report retrieval without re-running the audit.
Core audit and follow-up contact are covered, but there is no way to retrieve a prior report, re-check a fixed site, or list past audits, creating dead ends for iterative workflows.
Grades a public website out of 100 (A–F) across speed & mobile (including Google's live PageSpeed mobile test), Google visibility (SEO), trust & security, and lead capture. Returns every problem ranked by impact with a plain-English fix, what already works, and a link to a shareable full report. Use when the user asks to audit, grade, check, review or analyse a website, its SEO, speed or conversion. Takes 10–40 seconds.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The website address, e.g. example.com or https://example.com/page |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnly, idempotent, openWorld, non-destructive, so safety is covered. The description adds meaningful context: it runs Google's live PageSpeed mobile test, takes 10–40 seconds, returns ranked problems with plain-English fixes, what works, and a shareable report link. This tells the agent the call is slow and external-network-dependent, beyond what annotations state.
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?
Three sentences, front-loaded with what it does and the output shape, then usage triggers, then runtime. It is dense but every sentence carries useful information; 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?
For a one-parameter, read-only audit tool with no output schema, the description covers purpose, output deliverables, runtime, and usage triggers. Nothing an agent needs in order to call it 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?
Schema coverage is 100%, so the schema documents the url format. The description adds only implied meaning about the URL being a public website address, which is marginal but confirms the resource must be publicly accessible. Baseline 3 would also be defensible, but the 'public website' constraint adds a real semantic requirement not in 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?
States a specific verb (grades) and resource (public website) with clear scope: scores out of 100 across named categories. The description distinguishes the resource and output shape well enough that an agent knows exactly what the tool produces.
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 says when to use: 'Use when the user asks to audit, grade, check, review or analyse a website, its SEO, speed or conversion.' No alternatives or exclusions are named, and the only sibling is request_help, so a 4 is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Sends the user's request for help fixing their website to Soofi Digital's team, who will contact them by email or WhatsApp. Only use when the user explicitly asks for help or for Soofi Digital to contact them, and only with contact details the user has given you for this purpose. Confirm the details with the user before sending.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | The user's name | |
| Yes | The user's email address | ||
| phone | No | Optional WhatsApp/phone number with country code, e.g. +1 555 123 4567 | |
| message | No | Optional: what they want help with, in their words | |
| website | Yes | The website they want help with | |
| business | No | Optional business name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare openWorldHint=true, readOnlyHint=false and idempotentHint=false, so the write/external nature is partially covered. The description adds value beyond them by disclosing the human follow-up channel and the consent constraints (user-provided contact details only, confirm before sending) — a side-effect and privacy posture the annotations cannot express.
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?
Three sentences, front-loaded with what the tool does and what happens next, then the constraints. Every sentence carries a distinct obligation with 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?
Covers purpose, preconditions, consent handling and the out-of-band outcome, which is what an agent needs for a low-complexity, flat-schema submission tool. It says little about failure or duplicate-submission behavior, but nothing essential is missing for correctness.
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 all six fields including optional phone, message and business are already documented. The description only adds a provenance rule for the contact details ('details the user has given you'), not new field semantics, 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 and resource ('sends the user's request for help fixing their website') plus the destination and follow-up channel (Soofi Digital's team contacting by email or WhatsApp). This clearly distinguishes it from the sibling audit_website, which analyzes a site rather than forwarding a request to a human team.
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 gate: 'Only use when the user explicitly asks for help or for Soofi Digital to contact them, and only with contact details the user has given you for this purpose.' It also imposes a procedural prerequisite ('Confirm the details with the user before sending'), leaving the agent with no ambiguity about when to call it.
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.
audit_websiterequest_helpFree website score for speed, SEO, security and AI search readiness, with the fixes.
The website checker for AI agents. One call: verdict, score out of 100, fix list.
Check a deployed web app for security headers, SEO, accessibility and performance, with a grade.
Free website analyzer: score any public URL 0-100 across 8 quality dimensions. No auth.
Add one secure layer between your agents and this server.