Return the CycloneDX 1.6 VEX document for one of the caller's products.
Reads from the 24h ProductVexCache; if the cache is empty/expired the
next call to ``get_product`` (or the REST endpoint) will regenerate it.
Carries the same ``kernelscan.io:exploit_maturity`` /
``kernelscan.io:kev`` properties as the REST download (backend#337).
| Name | Required | Description | Default |
|---|---|---|---|
| product_id | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
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 the 24h ProductVexCache, the regeneration trigger via get_product or REST, and the specific kernelscan.io:exploit_maturity/kernelscan.io:kev properties. This gives agents realistic expectations about freshness and output content.
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 front-loaded with the core purpose and follows with relevant behavioral details. Minor internal references such as backend#337 add limited value, but the overall length is appropriate and each sentence 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?
Given the simple input schema and the absence of an output schema, the description provides enough context: output format, caching, property fields, and caller scope. Some form of error handling or access-control notes could round it out, but it is sufficiently complete for an agent to select and invoke the 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?
The only parameter, product_id, has zero schema description coverage. The description adds a useful scope constraint (the product must belong to the caller), but it does not explain the expected format, where to obtain the ID, or what happens when the called product is not the caller's. Some compensation is present, but not enough for full clarity.
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 opens with a specific verb and resource: 'Return the CycloneDX 1.6 VEX document for one of the caller's products.' This clearly identifies what the tool does and how it differs from sibling tools like get_product (product data) and get_cve (CVE data).
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 gives no explicit guidance on when to choose this tool over alternatives such as get_product or list_products. It mentions get_product only in the caching note, not as a competing tool. Usage context is left entirely to inference from the tool name and purpose.
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 targets a distinct resource and action: product lifecycle (create/get/list/update), CVE lookup/search, VEX retrieval, access request, support submission, and identity/quota check. There is no overlap; even create_product and update_product are clearly differentiated by their operation semantics.
All tool names follow a consistent verb_noun pattern (create_product, get_cve, list_products, etc.) using lowercase with underscores. The only outlier is whoami, which is a standard Unix-style command and fits naturally.
10 tools is well-scoped for the domain of Linux kernel security scanning and CVE/product management. Each tool serves a clear purpose without redundancy or bloat, covering the core workflows without overwhelming the agent.
The tool set covers the major lifecycle for products (create, get, list, update) and CVEs (search, get), plus VEX retrieval and account context. Minor gaps exist such as product deletion or direct config upload, but these can be worked around via existing tools and the REST API.