Skip to main content
Glama

ck_validate

Read-onlyIdempotent

Validate code, config, shell commands, or text against policy before execution. Returns violations and blocks unsafe actions.

Instructions

Validate proposed code, config, shell commands, or text against CK policy before execution. Read-only — no changes are applied to the project. Returns a validation result with any policy violations as findings. content is required. kind classifies the artifact (code/config/shell/text) for policy routing. source_type identifies the content's origin (developer, tool_output, human_review, issue, pull_request, web) for trust-boundary checks; untrusted sources receive stricter scrutiny. domain_pack applies a domain-specific policy pack (e.g., hipaa, owasp). requested_capabilities declares what the content needs (network, filesystem, shell, deploy) so the trust boundary can evaluate the request. Call ck_validate before writing files, running shell commands, or executing generated code. If validation returns blocked findings, do not proceed — use ck_finding to record them.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
artifact_typeNoCanonical artifact type. Compatibility aliases `instruction` and `text` are accepted and normalized to `source`.
contentYesThe content to validate or process: source code, config text, shell command, or freeform text.
domain_packNoDomain-specific policy pack to apply during validation.
intended_useNoHow the validated content will be used after validation.
kindNoArtifact kind classification for validation routing.
pathNoFile or directory path relative to the project root.
policy_packsNoAdditional explicit policy packs to apply. Currently supports ai_tools for AI tool configuration review.
requested_capabilitiesNo
security_workflow_phaseNoCanonical workflow phase. Compatibility aliases such as `preflight`, `analysis`, and `pre_edit` are accepted and normalized.
session_idNoUnique session identifier for correlating findings, proofs, budget, and audit trail.
source_typeNoOrigin category of the record (e.g., developer, tool_output, human_review).
target_scopeNoDeployment scope of the artifact being validated.
task_idNoTask identifier within the session for scoped operations.
trust_levelNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
advisoryNo
allowedNo
decisionNo
findingsNo
fix_promptsNo
precedentNo
scanned_atNo
summaryNo
trust_policy_advisoryNo
Behavior5/5

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

The description accurately reflects the readOnlyHint and idempotentHint annotations by stating 'Read-only — no changes are applied.' It adds behavioral context beyond annotations, such as policy routing by kind and stricter scrutiny for untrusted source_types.

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?

The description is concise and well-structured. It front-loads the primary purpose, then efficiently adds usage guidelines and key parameter explanations. Every sentence contributes value without redundancy.

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?

Given the tool's complexity (14 parameters, 1 required) and the presence of an output schema, the description covers essential aspects: validation purpose, when to invoke, and critical parameter semantics. It also directs the agent to related tools for blocked findings. The output schema handles return value details.

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

Parameters4/5

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

While schema coverage is high (86%), the description adds meaningful context for several parameters: content is required, kind classifies for policy routing, source_type influences trust-boundary checks, domain_pack applies domain-specific policies, and requested_capabilities are declared for evaluation. This enhances understanding beyond the enum descriptions.

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 clearly identifies the tool's purpose: validate proposed code, config, shell commands, or text against CK policy before execution. It specifies the verb 'Validate' and the resource, and distinguishes it from siblings by emphasizing it's a pre-execution check.

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

Usage Guidelines5/5

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

Explicitly states when to use: 'Call ck_validate before writing files, running shell commands, or executing generated code.' Also provides guidance on blocked findings: 'do not proceed — use ck_finding to record them.' This clarifies when not to proceed and suggests an alternative tool.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/aryaminus/controlkeel'

If you have feedback or need assistance with the MCP directory API, please join our Discord server