Shadow-AI posture (part of Code Security): unsanctioned / unknown AI-service usage discovered in code — totals, risk score, provider/type breakdown, hardcoded-key count, and top discoveries. Company latest, or one scan with scan_id. Reads code_review ShadowAIReport/ShadowAIDiscovery.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max discoveries to return | |
| scan_id | No | Optional CodeReviewScan id; company-wide latest if omitted |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It indicates the tool reads from code review data (ShadowAIReport/ShadowAIDiscovery) but does not disclose side effects, authentication needs, or limitations. The tool appears read-only but this is not explicitly confirmed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with three sentences, front-loading the main purpose and key outputs. Every sentence adds unique information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 parameters, no output schema), the description is fairly complete. It lists the contents of the response and usage modes. However, it omits details on result ordering, pagination, and the default limit behavior, which could be improved.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description minimally adds to the schema by clarifying that scan_id selects a specific scan or defaults to company-wide latest, but it does not explain how limit affects results (e.g., pagination or ordering). The value added is marginal.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states what the tool does: discover unsanctioned AI service usage in code. It specifies the type of data returned (totals, risk score, breakdown, hardcoded-key count, top discoveries) and distinguishes itself from sibling tools like code_review_scan or get_insights by focusing specifically on shadow AI posture.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving shadow AI posture but does not explicitly guide when to use this tool over alternatives like get_insights or compliance_scan. It mentions that scan_id is optional but lacks guidance on prerequisites or frequency of use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have distinct purposes (e.g., apply vs. get remediation, scan vs. status). A few pairs like get_insights and get_diagram_summary overlap slightly in metrics but descriptions clarify differences. No major ambiguity.
Predominantly verb_noun pattern (apply_, get_, generate_). However, code_review_scan and compliance_scan are noun phrases without a leading verb, and compliance_status is noun_noun, introducing minor inconsistency.
15 tools is at the upper end of typical but still reasonable for a security platform covering scanning, remediation, threat modeling, billing, and reporting. Each tool serves a clear function; no obvious bloat.
Covers core workflows: code/cloud/compliance scanning, threat modeling, remediation (dry-run and apply), traceability, insights. Minor gaps like missing scan listing or account management, but these align with the platform's assessment focus.