Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_poc_run

Destructive

Executes one approved proof-of-concept spec after validating signed authorization and single-use approval, re-linting, preflighting scope, enforcing limits, and capturing evidence.

Instructions

Execute one approved PoC spec. Requires a complete chain, a valid signed authorization covering the target and technique, and a signed single-use approval whose spec/code hashes still match; re-lints and preflights scope, then runs under hard limits and captures evidence. Refusals return a machine-readable reason. Never bypass the gate.

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>",
      "chain_id": "<chain_id>",
      "spec_id": "<spec_id>",
      "approval_id": "<approval_id>"
    },
    "name": "oc_poc_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
spec_idYes
chain_idYes
approval_idYes
engagement_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare destructive=true and openWorld=true, so the description's added value is what it says about gating: authorization must cover the specific target and technique, approval is single-use with matching spec/code hashes, scope is re-linted and preflighted at call time, execution is bounded by hard limits, evidence is captured, and refusals return a machine-readable reason. These are behavioral facts no annotation conveys.

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?

Front-loaded with the action and the gating requirements; nothing is filler. The semicolon-chained single paragraph runs long and packs multiple prerequisites together, which makes it denser than it needs to be for an agent parsing constraints.

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

Completeness5/5

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

For a destructive, open-world execution tool this covers prerequisites, in-flight behavior (re-lint, preflight, hard limits, evidence capture) and failure mode, while an output schema already documents return values. An agent has enough to decide whether to call it and what to expect when it is refused.

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%, so the description has to carry parameter meaning, and it partially does: it links chain_id to a 'complete chain' and approval_id to a signed single-use approval whose hashes must still match the spec. However it never explains engagement_id or spec_id individually, nor what makes an id invalid, so a real coverage gap remains.

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

Purpose5/5

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

'Execute one approved PoC spec' gives a specific verb and resource, and the surrounding clauses (re-lints, preflights scope, runs under hard limits) make clear this is the execution step rather than a lint/render/evidence sibling. An agent can distinguish it from oc_poc_lint or oc_poc_render without opening any schema.

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

Usage Guidelines4/5

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

The preconditions for use are explicit: a complete chain, a valid signed authorization covering target and technique, and a signed single-use approval whose hashes still match. 'Never bypass the gate' reinforces the boundary. It stops short of naming alternatives (e.g. lint-before-run), so exclusion guidance is implicit rather than spelled out.

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