Fetch a URL and audit its response for security-relevant HTTP headers (HSTS, CSP, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, Permissions-Policy). Flags missing/misconfigured headers with a score.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The URL to audit |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of disclosing behavior. It does reveal that the tool makes a network fetch and returns a score, which is helpful, but it does not explain the score range, what constitutes 'misconfigured', redirect behavior, or failure handling for unreachable URLs.
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?
One sentence delivers the action, the target, the specific headers audited, and the output format. No filler or redundant wording; every clause earns its place.
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, the description covers the essential invocation details: the URL to pass, the audit behavior, and the score plus flags as output. It could be richer by describing the score scale or failure cases, but the absence of an output schema does not leave the agent without a workable mental model.
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 fully documents the single 'url' parameter with 100% coverage. The description adds only that the URL is fetched for header audit, without extra format or constraint details, so it does not significantly enhance the schema's own description.
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 ('Fetch') and resource ('URL response') and precisely names the audit domain: security-relevant HTTP headers. It lists the exact headers checked and the outcome (a score with flags for missing/misconfigured values), which clearly differentiates it from broader audit siblings like seo_audit.
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 described behavior makes the intended use case clear: audit a URL's security headers. It does not explicitly name alternative tools or state when not to use it, but the focus on security headers provides enough context to distinguish it from the many sibling audit tools.
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.
Many tools audit overlapping site signals (seo_audit vs structured_data_extract vs tech_stack_fingerprint; page_performance_check vs pagespeed_insights; ssl_cert_check vs ssl_labs_grade; broken_link_check vs sitemap_url_validator), so an agent could initially pick the wrong one. Descriptions usually clarify the distinction, but the boundaries are not always obvious.
Most names follow a snake_case target+operation pattern (ssl_cert_check, email_deliverability_check), but check_open_ports and check_robots_sitemap reverse the order, and the action suffixes vary widely (check, audit, validate, lookup, extract, grade, report, insights). Still readable, but not a single predictable convention.
At 29 tools, the server is above the 25-tool threshold and feels like an undifferentiated grab bag of single-purpose audits rather than a tightly scoped toolkit. Many checks could be consolidated (e.g. the separate SSL and performance tools, or domain_report versus its component checks).
For a web/domain/email/security diagnostics toolbelt, the coverage is unusually broad: DNS, TLS, email, SEO, structured data, vulnerabilities, ports, redirects, and more are all represented. Minor gaps exist (no generic HTTP request/debug tool, no zone-transfer or full WHOIS history), but agents can accomplish most diagnostic workflows without hitting dead ends.