Skip to main content
Glama
Sign In
ai-secure-by-design

ai-secure-by-design

by ankush1982
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Plan a draft manifest

sbd_plan_init
Read-onlyIdempotent

Preview the privacy-security manifest an init command would generate: detect the stack and personal-looking fields, return a draft with TODO(user) markers, and write nothing.

Instructions

Detect the stack and personal-looking fields, and return the draft manifest sbd init --non-interactive would write, with TODO(user): markers. Never classifies a field or picks a regime. Writes nothing; an existing manifest is reported as a skip.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "sbd_plan_init"
  }
}

Input Schema

NameRequiredDescriptionDefault
stackNoThe stack, if the user chose one. Default: detection.
regimesNoRegime ids the user chose. Never fill these in yourself.
manifestPathNoManifest path relative to the workspace root. Default privacy-security-manifest.yaml.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: it explains that an existing manifest is reported as a skip rather than overwritten, and that output carries TODO(user): markers instead of classifications. This is useful disclosure beyond the structured fields.

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?

Three short sentences with zero redundancy, front-loaded with the core action and followed by the key non-behaviors. Every clause carries information an agent needs.

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

Completeness4/5

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

With no output schema, the description does the necessary work of describing the return value (a draft manifest with TODO(user): markers) and the skip case for existing manifests. Only minor gaps remain, such as what the detection result looks like when no stack is supplied.

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 100%, so the schema already documents stack, regimes, and manifestPath including the 'Never fill these in yourself' guidance on regimes. The description only reinforces the regimes constraint and adds no format or defaulting detail beyond the schema, so the baseline 3 is appropriate.

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?

States a specific verb and resource: detect the stack and personal-looking fields, then return the draft manifest that `sbd init --non-interactive` would write. The scope exclusions ('Never classifies a field or picks a regime') further pin down the boundary, so an agent can distinguish this planning step from stricter siblings like sbd_validate_manifest or sbd_plan_scaffold.

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?

The description implies usage context (draft the manifest before committing) and gives negative guidance ('never classifies a field or picks a regime', 'existing manifest is reported as a skip'), but it never names an alternative sibling such as sbd_plan_scaffold or says explicitly when to prefer this over them. Usage is inferable rather than stated.

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