check_sriLoads a public page and lists every script, stylesheet and preload it pulls in. For third-party files, checks whether an integrity= hash is present and matches, and returns a ready sha384 hash for files that have none.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public https page URL or domain, e.g. https://app.example.com/ |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds real value beyond that: it discloses network fetching of a live page, that only third-party files are hash-checked, and that a ready sha384 is synthesized for unhashed files. It omits failure behavior for unreachable or blocked pages and any rate/robustness limits.
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 tight sentences, each earning its place: the first establishes scope and what is enumerated, the second establishes the integrity analysis and the generated hash. Purpose is front-loaded with zero 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?
There is no output schema, so the description carries the return-value burden, and it does explain the shape of results (resource list, integrity presence/match, generated sha384). What is missing is behavior on fetch failure or non-public URLs, which matters for an open-world network tool.
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% with a single required 'url' parameter, and the schema already states 'Public https page URL or domain' with an example. The description only echoes 'public page' and adds no syntax, normalization or domain-vs-URL handling details, so the baseline of 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 specific verbs and resources: loads a public page and enumerates scripts, stylesheets and preloads, then verifies integrity hashes and emits a sha384 for those missing one. This is unambiguously distinct from the sibling tools (registry lock, DNS registrar, domain scan), so an agent can identify it without consulting the schema.
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 phrase 'public page' implicitly constrains applicability (no auth-protected or non-https targets), which gives some usage signal. However, there is no explicit when-to-use statement, no guidance on when to prefer scan_domain or the other check_* siblings, and no note on prerequisites or failure conditions.
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.