Given a website URL, returns a 0-100 AI Agent Readiness score with category breakdowns (structured data, metadata quality, agent discoverability, AI-bot friendliness) and concrete recommendations. Pure deterministic check, fast, no LLM call.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden and adds meaningful behavioral traits: 'Pure deterministic check, fast, no LLM call.' This informs the agent about cost, latency, and repeatability. It also clarifies the output includes recommendations, but does not mention any limitations or data source specifics.
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 concise and front-loaded with the primary purpose. It packs the mechanism, output, and key behavioral traits into a single readable sentence without redundancy. Every phrase contributes to the agent's understanding.
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 single-parameter tool with no output schema, the description is quite complete: it covers input, output structure, and key behavioral characteristics. It lacks explicit remarks on error handling or rate limits, but these are not critical for a simple deterministic URL check.
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 0%, so the description must compensate. It adds context by specifying 'website URL' rather than just a generic URL, and clarifies the input is an address to be scored. However, it provides no format guidance (e.g., protocol, domain requirements) beyond the schema's simple string type.
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 uses a specific verb ('returns a 0-100 AI Agent Readiness score') with a clear resource ('Given a website URL'). It distinguishes the tool from siblings by detailing the unique scoring output and category breakdowns, making its purpose immediately clear.
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 implies usage (when you need an AI readiness assessment) but does not explicitly state when to use this tool versus alternatives like get_wcag_audit or request_strategy_session. There are no exclusions or alternative suggestions, though the 'fast, no LLM call' hints at a context where speed/cost matters.
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 has a clear, distinct purpose. The get_* tools retrieve different data types (services, firm profiles, case studies, audit offerings), the request_* tools target different actions (introduction, quote, strategy session), and assess_ai_readiness and claim_listing are unique. No two tools appear to do the same thing.
Tool names are all snake_case and follow a verb_noun structure, but the verbs vary (assess, claim, find, get, request) rather than using a single consistent pattern. The get_ and request_ subgroups are internally consistent, so the naming is readable and predictable despite the variety.
With 10 tools, the server is well-scoped. Each tool serves a clear function in the marketing/directory domain: discovery (find, get), engagement (request, claim), and assessment (assess, get_wcag_audit). The count is neither sparse nor overwhelming.
The surface covers the core workflows: searching the directory, retrieving firm details and services, requesting intros/quotes/sessions, claiming listings, and checking AI readiness. Minor gaps exist (e.g., no tool to update a listing or access the compliance registry directly), but these are not likely to cause agent failures.
