Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_chain_plan

Validates CVE capability chains deterministically: checks step requirements/provided tokens, reports missing capabilities and cycles, attaches nuclei/trivy evidence, and persists the chain.

Instructions

Validate a CVE capability chain deterministically. Each step supplies requires/provides capability tokens, a written basis, and an optional evidence source; the tool computes satisfaction closure, missing tokens, and cycles, attaches nuclei/trivy artifact observations, and persists the chain. It never invents CVE semantics: annotate only what the advisory or evidence supports.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "engagement_id": "<engagement_id>",
      "steps": "<steps>",
      "entry_capabilities": "<entry_capabilities>"
    },
    "name": "oc_chain_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsYes
artifactsNo
chain_nameNo
engagement_idYes
entry_capabilitiesYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=false, so the safety profile is partly given. The description adds genuinely new behavior: it computes closure, missing tokens, and cycles, attaches nuclei/trivy observations, and persists the chain, plus the important constraint that it never invents CVE semantics. It does not say what happens on validation failure or whether a failed chain is still persisted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core action, then the step contract, then the guardrail against fabricating CVE semantics. Dense but every clause adds information; only the closing admonition is closer to policy than to tool behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained. For a mutating, persisting tool with 0% schema coverage and three required parameters, the description should still clarify what engagement_id and entry_capabilities mean and what occurs when the chain fails validation. As written, an agent knows the concept but not the full call contract.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 5 parameters, so the description carries the burden. It explains the shape of steps (requires/provides tokens, written basis, optional evidence source) and references artifacts via nuclei/trivy observations, covering roughly half the parameters. engagement_id, chain_name, and entry_capabilities receive no semantic explanation beyond their names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Validate') and resource ('CVE capability chain') and adds concrete outcomes: satisfaction closure, missing tokens, cycles, artifact attachment, and persistence. It is clear enough to distinguish from a generic chain-listing tool, but it never names a sibling such as oc_attack_chain or oc_chain_get to sharpen the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the verb 'Validate' and by the phrase 'annotate only what the advisory or evidence supports', which suggests the tool is for evidence-backed chain construction. There is no explicit when-to-use versus when-not guidance and no named alternative for building versus validating a chain, so the agent must infer the routing.

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

Deploy Server

Other Tools