Scan text — an agent skill, MCP server source, or plugin — for malicious behaviour before loading it. 17 attack patterns / 59 regex signatures across 4 severity levels — credential exfiltration, download-and-execute, prompt injection, command execution, seed-phrase harvesting and more.
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | File or snippet to scan |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses detection capabilities (17 patterns, 59 regex signatures, 4 severity levels, specific attack types) but does not explain what happens on detection (e.g., returns boolean, list of findings? errors?). This is adequate but leaves the return behavior ambiguous.
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, zero waste. The first sentence states the core purpose and use case; the second provides detailed security scope. Front-loaded and efficient.
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?
Given a simple single-parameter tool with no output schema, the description is nearly complete. It covers purpose, usage context, and technical scope. A minor gap is the lack of return value info, but for a scanning tool, the details provided are sufficient for most agents to decide to invoke and then interpret results.
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% (the single parameter 'content' has a brief description), so baseline is 3. The description adds context about what kind of content is expected (agent skill, MCP server source, plugin) which adds value beyond the schema's 'File or snippet to scan', but does not elaborate on format expectations.
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 ('scan') and resource ('text — an agent skill, MCP server source, or plugin') and clearly states the purpose: detect malicious behavior before loading. It distinguishes from siblings like audit_skill_url by focusing on text rather than URLs, and covers multiple attack categories.
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 explicitly states when to use this tool ('before loading' a skill/source/plugin) and hints at when not to (it's for text, not URLs — sibling audit_skill_url handles URLs). It implies a security screening context, which guides appropriate invocation.
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.
Most tools serve clearly distinct purposes: air quality, skill audit, country data, earthquakes, elevation, geocoding, holidays, URL reading, and web search. However, `audit_skill_text` and `audit_skill_url` both audit for malicious behavior, differing only in input type, which could cause slight confusion.
Tool names use a mix of snake_case and descriptive phrases without a strict verb_noun pattern. Some names are verbs (e.g., `geocode`, `audit_skill_text`, `read_url`), while others are nouns (e.g., `air_quality`, `earthquakes`). The naming is readable but inconsistent in style.
With 11 tools, the count is well-scoped for a server that aggregates diverse free data and security services. Each tool serves a distinct and useful function, and the `paid_catalogue` tool properly manages the paid extension without bloating the main set.
The tool set covers a broad range of data types (environment, economic, geographic, security), but for each individual domain, coverage is shallow. For example, only current air quality is provided (no historical data), and skill auditing only returns a scan result (no detailed remediation). The set lacks update, delete, or drill-down operations per domain.