score_urlGrade any public URL A–F across 20 weighted agent-readability checks, including llms.txt, schema.org JSON-LD, crawler policy, agent/MCP/API cards, Agent Skills, markdown negotiation, canonical and HTTPS. Free; returns which checks failed. The paid endpoint at /api/audit adds the reason and a paste-ready fix for each.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Absolute http(s) URL to grade. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses that the tool is free, returns a grade plus the list of failed checks, and covers a specific set of checks. It does not mention network-fetch behavior or rate limits, but the given details materially describe what happens.
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?
Two sentences deliver a high density of useful information: grade range, check count, example check categories, cost, failure output, and a paid upgrade path. Every clause earns its place and the core purpose is front-loaded.
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 tool has one simple parameter and no output schema, so the description must explain the return value — and it does: grade A–F plus which checks failed. It also covers pricing and the more detailed paid endpoint. A formal response schema is not stated, but the agent has enough to call the tool 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 coverage is 100% because the `url` parameter already explains it as an 'Absolute http(s) URL to grade.' The description adds the 'public' qualifier, but this is a minor addition beyond the schema, so the 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 ('Grade'), a resource ('any public URL'), and a concrete grading scale ('A–F across 20 weighted agent-readability checks'). It is immediately distinct from sibling tools like get_product or search_mcp_servers, so no ambiguity remains.
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 clearly says the tool works for 'any public URL' and draws a practical line between the free call (returns failed checks) and the paid endpoint (adds reasons and fixes). It does not explicitly name sibling alternatives, but the paid endpoint acts as the relevant alternative and the context is clear.
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.
Each tool targets a distinct resource or action: product retrieval, product search, registration guidance, URL scoring, MCP server search, and x402 endpoint search. Even where two tools search, their domains (self-registered products vs official MCP registry vs payable endpoints) are clearly differentiated in the descriptions.
Five of six tools follow a consistent verb_noun pattern (get_product, score_url, search_mcp_servers, search_products, search_x402_endpoints). The outlier is 'how_to_register', which uses a phrase instead of an imperative verb, creating a minor inconsistency.
With 6 tools, the server is well-scoped for its purpose: it covers discovery, retrieval, registration info, and auditing without overlap or bloat. This is well within the ideal 3-15 range.
The server offers search and get for products, specialized searches for MCP servers and x402 endpoints, a URL audit tool, and registration instructions. Missing are direct get-by-id actions for MCP servers and endpoints, but search results likely provide enough detail for the intended use.