Run a full agent-readiness scan on a website or MCP server URL. Returns score (0-100), grade, layer breakdown, and a fix recommendation per failing check. Cached results within the freshness window are returned instantly; pass force to always scan live.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Domain or URL to scan, e.g. stripe.com | |
| force | No | Bypass the freshness window and scan live | |
| mcpUrl | No | Optional MCP server URL to test alongside the site |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses caching behavior ('Cached results within the freshness window are returned instantly; pass force to always scan live') and mentions the return structure. However, it does not address potential side effects (e.g., network requests, timeouts), error handling, or whether the scan is destructive. The transparency is adequate but incomplete.
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 two sentences long, with the first sentence front-loading the action and output, and the second explaining caching behavior. Every word adds value; there is no repetition or filler. It is appropriately sized for a tool with 3 parameters and no output schema.
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?
The description explains the core purpose and return values (score, grade, layer breakdown, fix recommendation) but lacks details about the layer breakdown, the freshness window duration, error scenarios, and rate limits. Since there is no output schema, more context about the expected return structure would improve completeness. The description is adequate for a simple scan tool but has gaps.
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?
The input schema already provides descriptions for all three parameters (100% coverage). The description adds minimal value beyond the schema: it reinforces the force parameter's effect ('pass force to always scan live') and mentions the return type, but does not clarify the meaning of 'freshness window' or 'mcpUrl' beyond what the schema already states. Baseline 3 is appropriate given high schema coverage.
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 clearly states the action: 'Run a full agent-readiness scan on a website or MCP server URL.' It specifies the output (score, grade, layer breakdown, fix recommendation) and distinguishes the tool from sibling tools like get_checks or get_score by focusing on scanning a domain rather than retrieving existing data. The verb+resource+scope is specific and unambiguous.
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 provides no guidance on when to use this tool versus sibling tools (e.g., get_checks, get_score). It does not mention when not to use it, prerequisites, or alternatives. The only hint is the caching behavior, but that is not usage guidance. Without explicit context, an agent cannot determine if this tool is the best choice for a given task.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools are generally well-distinguished, but discover_products and search_capabilities could be confused since both search across domains. The difference in query type (task intent vs. capability) is somewhat subtle. Overall, most tools have clear, separate purposes.
All tool names use a consistent verb_noun pattern (e.g., discover_products, get_checks, scan_domain). The naming is predictable and matches the server's domain of evaluating agent-ready properties.
With 11 tools, the server covers scanning, scoring, feedback, and search without being overly broad. Each tool has a distinct role, and the count is appropriate for the focused purpose of assessing agent readiness.
The tool set covers the full lifecycle: discover/scan domains, get scores and checks, apply skills, verify with challenges, submit feedback and disputes. There are no obvious missing operations for the stated domain.