ai-secure-by-design

Validate manifest

sbd_validate_manifest

Read-onlyIdempotent

Validates privacy-security-manifest.yaml against JSON schema and semantic rules, returning findings to catch configuration errors before CI, git hooks, or deployment.

Instructions

Validate privacy-security-manifest.yaml against schemas/manifest.schema.json plus semantic checks. Returns findings.

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_validate_manifest"
  }
}

Input Schema

Name	Required	Description	Default
`manifestPath`	No	Manifest path relative to the workspace root. Default privacy-security-manifest.yaml.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 5, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered without the description. The description adds real value by disclosing the validation target (schemas/manifest.schema.json) and the two-stage check (schema + semantic), but it does not say whether problems surface as findings, thrown errors, or exit status, nor how failures differ from a clean result.

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?

Two compact sentences, both front-loaded with the most decision-relevant information (what is validated, against what). The closing 'Returns findings' is terse to the point of being underspecified, which is the only real cost; there is no filler.

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?

For a simple single-parameter read-only validator, the essentials are present, and annotations handle safety. However, with no output schema, the description's entire account of the return value is 'Returns findings' — it does not convey shape, severity levels, or whether a failing manifest is an error or a normal result, which is the main thing an agent needs to interpret the response.

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?

There is a single optional parameter with 100% schema description coverage, including its default, so the schema already carries the semantics and the baseline of 3 applies. The description never mentions the path parameter or what happens if it is omitted (schema says default privacy-security-manifest.yaml), adding nothing beyond structured data.

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 a specific resource ('privacy-security-manifest.yaml'), and adds that validation covers both the JSON schema and 'semantic checks', which tells an agent this is more than a schema lint. It does not name or contrast with any sibling (e.g., sbd_scan_text, sbd_review_diff), so the differentiation is inferable rather than explicit.

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: use this when you have (or default to) a manifest file and want it checked. There is no explicit when-to-use statement, no when-not-to-use, and no mention of alternatives such as sbd_scan_text or sbd_review_diff for other validation needs, so an agent must infer routing from the tool name alone.

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

Deploy Server