Supply-chain malware check against OpenSSF/OSV. USE WHEN: about to suggest install of an unvetted/unfamiliar package; name came from a blog/tutorial. Call BEFORE check_package for untrusted pkgs. RETURNS: {is_malicious, threat_tier, source}.
| Name | Required | Description | Default |
|---|---|---|---|
| package | Yes | ||
| ecosystem | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive. The description adds the return shape '{is_malicious, threat_tier, source}' and the ordering recommendation relative to check_package, providing useful context beyond annotations.
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?
Three sentences with clear markers (USE WHEN, RETURNS) and no filler. Every sentence contributes meaningful guidance.
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 simple read-only lookup with two parameters and no output schema, the description covers purpose, usage context, and return contract. It omits edge cases like unknown packages or rate limits, but these are minor given the tool's simplicity and annotation coverage.
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 coverage is 0% and the description gives no parameter details. The schema provides an enum for ecosystem but 'package' is a bare string; the description does not clarify package name formatting, version inclusion, or other nuances.
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 'Supply-chain malware check against OpenSSF/OSV', clearly stating the tool's function and data source. It also distinguishes from sibling check_package via the directive 'Call BEFORE check_package for untrusted pkgs'.
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?
Explicitly provides 'USE WHEN: about to suggest install of an unvetted/unfamiliar package; name came from a blog/tutorial' and 'Call BEFORE check_package for untrusted pkgs'. This gives clear conditions and an alternative tool.
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 specific, well-defined function with clear use cases. Overlapping functions like check_package and get_package_prompt are explicitly differentiated by output format and cost. No tools are ambiguous.
Almost all tools follow a verb_noun pattern (check_, get_, find_, etc.). The only exception is 'package_exists', which uses noun_verb, creating a minor inconsistency. Overall consistent and predictable.
22 tools is slightly above the typical 3-15 range but each tool earns its place by addressing a distinct aspect of dependency analysis. The count is reasonable for a comprehensive security and health tool.
The tool surface covers the full lifecycle of dependency evaluation: existence, health, vulnerabilities, malware, compatibility, migration, trending, trust signals, error resolution, and project scanning. No obvious gaps exist.
