detect_secretsUse before an agent logs, stores, or forwards text that may contain credentials. Finds likely API keys, private keys, JWTs, cloud credentials, and secret patterns without echoing values. Trial, subscription, or x402 pay-per-call.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare the tool as read-only, idempotent, and non-destructive, so the safety profile is covered. The description adds valuable behavioral detail by stating 'without echoing values,' which clarifies a non-obvious privacy guarantee beyond what annotations imply. This is meaningful extra context about the tool's output behavior.
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 three sentences, each serving a distinct purpose: usage timing, detection scope and non-echoing behavior, and payment model. It is front-loaded with the actionable 'Use before...' instruction, and no word is wasted. It is an ideal length for a simple tool.
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 (one parameter, no output schema), the description covers the essential context: when to use, what it detects, and its non-echoing guarantee. The only minor gap is that it does not describe the return format or type, but since the tool is a detector, the agent's main need is to know when to call it, which is well covered.
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?
The schema has only one parameter ('text') with no property description (0% schema description coverage). The description compensates by specifying that the parameter is 'text that may contain credentials,' giving semantic meaning to the input. Since this is the only parameter, this level of explanation is sufficient for invocation.
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 the tool's function with a specific verb ('Finds') and resource ('likely API keys, private keys, JWTs, cloud credentials, and secret patterns'), making its purpose unmistakable. It also specifies that it detects without echoing values, which adds scope. This distinguishes it from sibling tools like redact_sensitive_text or scrub_text, even though no explicit sibling comparison is made.
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 provides an explicit usage context: 'Use before an agent logs, stores, or forwards text that may contain credentials.' This tells the agent when to invoke the tool. However, it does not explicitly mention when not to use it or name alternative tools for cases where redaction or other processing is needed, so it falls short of a full 5.
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.
The tool set covers two domains (text processing and agent infrastructure) with many specialized tools. Text tools like inspect_text, scan_untrusted_text, sanitize_agent_context, and prepare_for_agent have overlapping risk signals but descriptions clarify distinct purposes. Action infrastructure tools like manage_action_challenge, manage_action_quorum, manage_action_reconciliation are well-differentiated but numerous, leading to potential confusion for an agent selecting among them.
All tools use snake_case with a verb_noun pattern (e.g., check_action, manage_task_contract, scrub_text). The verbs are diverse (check, manage, create, delete, record, inspect, etc.) but consistently applied. A few deviations like fingerprint_action and lock_action_intent still follow the style. Overall, the naming is predictable and homogeneous.
49 tools is excessive for a typical MCP server. The server tries to combine text preprocessing (10-12 tools) with a comprehensive agent infrastructure (30+ tools) into one surface. While each tool may serve a purpose, the count overwhelms the typical scope, making it hard for an agent to navigate efficiently.
The text processing suite covers scrubbing, inspection, redaction, validation, and detection thoroughly. The agent infrastructure covers idempotency, approval, signals, leases, budgets, deadlines, handoffs, and reconciliation. There are no obvious missing lifecycle states for the intended advanced agent framework. Minor gaps exist, such as no tool to list all active locks or signals, but these are likely out of scope.