vulnforge_audit_zkp_gateway

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

With no annotations, the description carries the full disclosure burden. It does volunteer that the tool performs "automated policy synthesis and canary sandbox verification," which hints at active execution rather than pure static reading. But it never states whether the audit is read-only, whether files or sandbox environments are mutated, what permissions are required, or what happens to a disabled gate (destroyed vs. reported).

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?

Front-loaded with the verb and primary resource, then structured as a scannable parenthetical list of CWE-scoped vectors. It is a single dense sentence, and the eight-item CWE enumeration is long but each entry earns its place by defining audit coverage. Slightly over-packed but not wasteful.

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, no-output-schema, no-annotation audit tool, an agent still lacks crucial context: what the result looks like (findings list? pass/fail per vector? synthesized policy output?) and how the canary sandbox step reports back. The input side is thoroughly covered, but the return/side-effect side is not, and with no output schema the description must compensate—it only partly does.

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 schema already documents every parameter including the enum, defaults (300s, true, true), and the optional proof payload shape. The description adds nothing about parameter interplay—e.g., how format override interacts with auto-detection or how maxProofAgeSeconds feeds CWE-613 checks—so baseline 3 is appropriate.

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") and a precise resource set (ZKP verification gates, Groth16/Plonk circuits, W3C VC revocation registries, DID gateways), then enumerates eight named vulnerability vectors with CWE IDs. This is unmistakably distinguishable from every sibling (eBPF, IAM, vault, SBOM, etc.), none of which touch ZKP/circuit semantics.

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 enumeration of supported artifact formats and CWE classes makes the "when to use" condition clear by domain. However, it never names an alternative or states exclusions (e.g., when to prefer vulnforge_audit_pqc for post-quantum proofs, or vulnforge_audit_api for the surrounding REST surface), leaving routing to inference.

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