Strip scripts and unsafe markup. Keeps a short allow-list of tags.
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "html_sanitize"
}
}| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, and it does disclose the core semantics: unsafe constructs are removed and a short allow-list of tags is preserved. It is silent on important traits an agent would want — whether attributes and event handlers are stripped, whether the operation is lossy, and how the HTML is supplied (i.e., that the request body is the HTML string).
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 short sentences, action first and the allow-list caveat second, with no filler or redundancy. Every sentence contributes distinct information.
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 stateless, zero-parameter text transform with no output schema, the description covers what goes in and what is preserved or removed. Slightly more detail on the input medium (raw HTML in the body) and the allow-list breadth would close the remaining gap, but nothing essential is missing.
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?
There are zero declared parameters, which is baseline 4; the description has no parameter semantics to add. The one residual gap is that the schema is an open POST body with no properties, so the description could have said the body itself is the HTML to sanitize, but the rubric baseline 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?
The description names a specific verb and resource ("Strip scripts and unsafe markup") plus a scope note on the allow-list, so the agent knows exactly what the tool does. It does not explicitly distinguish itself from siblings, but none of the listed siblings (base64, hash, json_format, etc.) overlap, so differentiation is implicit rather than stated.
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?
Usage is implied by the purpose: use it when you have untrusted HTML and want it safe. There is no explicit when-to-use/when-not framing, no mention of what to do with the output, and no named alternative for the case where only escaping (rather than stripping) is wanted.
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.