auditAudit a package's dependencies for risks.
Checks each dependency for retired versions, stale packages, single-owner packages, and known vulnerabilities via OSV.dev.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Package name on hex.pm | |
| version | No | Release version (defaults to latest) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses the types of risks checked (retired versions, stale packages, single-owner, vulnerabilities), which adds transparency beyond the input schema. However, with no annotations, it does not mention whether the operation is read-only or has any side effects.
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, front-loaded with purpose, followed by specifics. No extraneous text, every sentence adds value.
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?
Describes what checks are performed but does not mention the output format or structure. With no output schema, more detail on return values would be helpful for completeness.
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 description clarifies that the 'name' parameter refers to a package whose dependencies are audited, adding context beyond the schema's 'Package name on hex.pm'. The version parameter's purpose (defaults to latest) is clear from schema, and description does not conflict.
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?
Clearly states it audits a package's dependencies for risks, listing specific checks. However, does not explicitly differentiate from sibling tool 'audit_mix_deps', which may have a different scope (local vs published).
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?
No explicit guidance on when to use this tool versus alternatives like 'audit_mix_deps' or 'health'. Usage is implied from the description but lacks when-not or exclusion criteria.
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 have clearly distinct purposes, but 'audit' and 'audit_mix_deps' overlap in auditing dependencies, and 'dependencies' vs 'dep_tree' are related. Overall, the toolset is well-differentiated.
Tool names use snake_case consistently, but there is a mix of verb-based (search, compare) and noun-based (health, info) names, plus single-word vs compound names. Minor inconsistency but still predictable.
19 tools cover the Hex.pm ecosystem comprehensively without being overwhelming. Each tool addresses a specific need like searching, documentation, auditing, and dependency analysis.
The toolset covers major use cases: search, info, versions, documentation, dependencies, audit, health, and comparisons. Missing perhaps a tool for direct package source retrieval, but overall very thorough.