Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_poc_spec_create

Creates one declarative PoC spec per chain step, defining technique, in-scope target, bounded requests, assertions, and limits, while validating the target against the engagement and step. No rendering or execution.

Instructions

Create one declarative PoC spec for a chain step: technique class, in-scope target, bounded request list, closed assertion language, and limits. Validates the target against the engagement and the chain step. Does not render or execute anything.

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>",
      "step_order": "<step_order>",
      "technique": "<technique>",
      "target": "<target>"
    },
    "name": "oc_poc_spec_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
notesNo
limitsNo
sourceNo
targetYes
chain_idYes
requestsNo
techniqueYes
assertionsNo
step_orderYes
engagement_idYes
allow_insecure_tlsNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations declare non-read-only, non-destructive, non-open-world, non-idempotent, and the description reinforces this by stating nothing is rendered or executed and that validation against engagement/chain step can occur. That adds genuine context beyond the flags, but it omits what happens on validation failure, whether the spec is persisted, and whether re-creating the same step duplicates it (relevant given idempotentHint=false).

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

Conciseness5/5

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

Two tight sentences, front-loaded with the create action and its scope, followed by the validation constraint and the negative scope. No filler and no restatement of the tool name.

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 described, and the core intent is covered. For an 11-parameter tool with three free-form object parameters, though, the description leaves the agent guessing about the structure of requests/assertions/limits and about allow_insecure_tls, which is the one parameter with security implications.

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?

With 0% schema description coverage the description must carry parameter meaning, and it does name technique, target, requests, assertions, and limits, with 'chain step' implying chain_id/step_order and validation implying engagement_id. However it never explains allow_insecure_tls, source, or notes, and the internal shape of the requests/assertions/limits objects ('closed assertion language' is a hint, not a specification) remains undocumented in both places.

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?

The description gives a specific verb ('Create one declarative PoC spec') and a precise resource scoped to a chain step, then enumerates the constituent parts (technique class, target, requests, assertions, limits). The closing clause 'Does not render or execute anything' positively separates it from render/run/lint siblings, so an agent can distinguish it without opening the 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?

It establishes clear context: this is the spec-authoring step of a chain, and the target is validated against both the engagement and the chain step, which tells the agent prerequisites must already exist. It stops short of explicitly naming when to choose this over oc_poc_lint or oc_poc_render, though the 'does not render or execute' clause implies the handoff order.

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