vulnforge_audit_sbom

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and delivers on the detection side: it names concrete threat classes (dependency confusion CWE-427, typosquatting CWE-829, event-stream compromise, wildcards CWE-1104, lifecycle scripts, integrity hashes, NTIA/EO 14028). It never states that this is a read-only analysis with no mutation, whether it reads from disk versus only the supplied content string, or anything about result shape or cost.

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?

A single front-loaded sentence with the verb and resource first, then the detection catalogue. Dense but every clause is informational; the CWE identifiers and famous-package examples could be trimmed slightly without loss, but nothing is filler.

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 7-parameter tool with no annotations and no output schema, the description covers inputs and detection scope but leaves the agent without any sense of what the audit returns (findings list? severity? compliance verdict?) or how the interacting parameters compose. Adequate to select the tool, thin for predicting the result.

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%, so the baseline of 3 applies — every parameter including the format enum and the packageManifestContent alias is already documented in the schema. The description adds only indirect mapping (its format list mirrors the enum), and does not clarify the overlapping content/packageManifestContent parameters or the npmrcContent+internalScopes pairing.

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?

States a specific verb (Audits) plus a precisely enumerated resource set: SBOM formats (CycloneDX, SPDX), package manifests (package.json, Cargo.toml, requirements.txt), and registry configs (.npmrc). The dependency-supply-chain focus clearly separates it from sibling audit tools covering eBPF, IAM, containers, GraphQL, cosign, etc.

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 resource enumeration — you audit a manifest when you have one — and the schema notes format is auto-detected when omitted. But there is no explicit when-to-use/when-not, no mention of when to reach for vulnforge_full_scan instead, and no stated prerequisites (e.g., supplying internalScopes alongside npmrcContent).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.