Skip to main content
Glama

ck_finding

Record policy compliance findings with a governance decision (allow, warn, block, or escalate) to build a durable audit trail. Use for validation failures, security checks, or human reviews.

Instructions

Persist a governed finding with a ruling decision (allow, warn, block, escalate_to_human). Findings are the durable audit trail in ControlKeel: every policy check, validation failure, or human review should produce a finding. Write operation — creates or updates a DB record. Idempotent for the same rule_id within a session. Returns the finding ID, status, and ruling state. Required fields: session_id, category (e.g., security/compliance/performance), severity (critical/high/medium/low), rule_id (dotted policy identifier such as CK-SEC-001), and plain_message. decision defaults to block; use allow for approved exceptions. Use ck_finding to record issues discovered during agent work; use ck_memory_record for general knowledge or decisions not tied to a policy rule.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
categoryYesFinding category (e.g., security, compliance, performance).
decisionNoGovernance decision: allow, warn, block, or escalate to human.
metadataNo
plain_messageYesHuman-readable finding description.
rule_idYesPolicy rule identifier that triggered this finding.
session_idYesUnique session identifier for correlating findings, proofs, budget, and audit trail.
severityYesSeverity level (e.g., critical, high, medium, low).
task_idNoTask identifier within the session for scoped operations.
titleNoHuman-readable title for display and search.
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses that it is a write operation (creates or updates DB record), is idempotent per rule_id within a session, and returns the finding ID, status, and ruling state. It could mention more about side effects or auth, but it covers the core behavioral traits well.

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?

The description is front-loaded with the main purpose and well-organized. It is slightly lengthy but each sentence adds useful information. Minor redundancy in listing required fields again could be trimmed, but overall it is efficient.

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?

Given no output schema, the description explains return values. It covers usage guidelines, parameter context, and behavioral traits. It does not discuss error conditions or failure modes, but the overall context is sufficient for an agent to use the tool correctly.

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?

Schema description coverage is 89%, so the bar is lower. The description adds value by explaining the default for 'decision' (block) and recommending 'allow' for exceptions, and by listing required fields again for emphasis. This supplements the schema descriptions effectively.

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 states the verb (persist), resource (governed finding with ruling decision), and distinguishes from siblings (ck_memory_record) by explicitly contrasting use cases. It provides a specific, actionable purpose.

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?

The description explicitly states when to use this tool versus alternatives ('Use ck_finding to record issues... use ck_memory_record for general knowledge'), explains the default decision value, and notes idempotency for same rule_id within a session.

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