agents

tool-call-guard

Pre-execution safety oracle for agent actions: submit the tool call you are about to run (shell, http, sql, file, code, env) plus your stated intent, and get a machine-enforceable verdict before you execute it. Decodes what the call does, flags the danger toolkit (rm -rf, reverse shell, curl|sh, SSRF to cloud metadata, credential reads, DROP/DELETE-without-WHERE, path traversal, dynamic eval), and binds it to your intent (allowedHosts/allowedPaths/readOnly/noNetwork) - only a fully pinned, clean, intent-matched call is auto-exec-safe. Hybrid: a deterministic, uninjectable detector engine (authoritative) plus an LLM classifier that can only raise the risk. Fails closed. Detection of known-dangerous patterns, not a proof of safety; it never executes the call. [security; up to 8c/call]

Input Schema

TableJSON Schema

Name	Required	Description
`call`	Yes	The tool call you are about to execute.
`intent`	No	What this call is for (natural language). Used by the classifier for intent-mismatch.
`context`	No	Optional: where the task/input came from (untrusted source label).
`expected`	No	Machine-checkable constraints. Supplying them lets the verdict BIND the call; only a positively-scoped, satisfied call is auto-exec-safe.

TDQS

A4/5.0

Behavior4/5

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

The description details the hybrid detector engine, failure modes (fails closed), dangerous patterns flagged, and that it never executes the call. With no annotations, it carries full burden and does well, though it omits latency or output structure.

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 a single paragraph that front-loads the main purpose and adds specific details. It is somewhat lengthy but each sentence is informative, avoiding redundancy.

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?

No output schema exists, so the description should explain the verdict structure. It mentions 'machine-enforceable verdict' and 'auto-exec-safe' but does not specify the response format or fields, leaving some ambiguity for an agent.

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?

Schema coverage is 100%, so baseline is 3. The description mentions the call and intent parameters but adds no new meaning beyond the schema's own descriptions for each property.

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 title 'tool-call-guard' and description clearly state the tool is a pre-execution safety oracle that accepts a tool call and intent, returning a verdict. It distinguishes itself from siblings like inject-guard by focusing on dangerous patterns across multiple action types.

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

Usage Guidelines4/5

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

The description explicitly says to use this tool before executing a call, and mentions it provides a machine-enforceable verdict. However, it does not state when not to use it or list alternatives, though the sibling tools imply different use cases.

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

All agents tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0

Disambiguation5/5

Each tool targets a distinct security domain: prompt injection, secret scanning, code review, transaction safety, tool call safety, and x402 trust audit. Despite overlapping themes, their purposes are clearly differentiated by detailed descriptions.

Naming Consistency3/5

Tool names use a mix of patterns like verb-noun (inject-guard, sign-guard), noun-verb (secret-scan), and noun-noun (pr-summary, x402-trust-audit). The consistent use of lowercase and hyphens helps readability, but the lack of a uniform verb_noun pattern lowers consistency.

Tool Count5/5

Seven tools is a reasonable number for a security-focused server covering multiple guardrails and utilities. Each tool earns its place without overwhelming the agent.

Completeness4/5

The set covers core agent safety areas: input guardrails, secret detection, code review, transaction verification, and tool call safety. The inclusion of a PR summary tool is slightly out of scope, but overall coverage is strong with minor gaps like audit logging.

Resources

Need Help?