Agent Utility MCP

by dev.workers.insivotron.agent-utility-mcp

analyze_tool_call

Read-onlyIdempotent

Analyze a proposed AI-agent tool call before execution and return a deterministic, policy-aware decision (allow, notice, confirm or block) covering destructive actions, sensitive-data exposure, external transmission, privilege changes and irreversible operations, under the applicable policy — permissive, balanced or strict, balanced by default. Filesystem paths outside a known workspace_root are treated as higher risk than paths inside it.

Input Schema

TableJSON Schema

Name	Required	Description
`policy`	No	Optional policy used to compute the decision: permissive, balanced or strict (default: balanced).
`context`	No	Optional declarative context about the proposed operation.
`arguments`	Yes	The proposed tool arguments. They are analyzed as data and never executed.
`tool_name`	Yes	The exact name of the proposed tool.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`risk`	Yes
`valid`	Yes
`checks`	Yes
`signals`	Yes
`decision`	Yes
`tool_name`	Yes
`risk_score`	Yes
`policy_applied`	Yes
`schema_version`	Yes
`ruleset_version`	Yes
`context_completeness`	Yes

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds significant behavioral context by listing the categories of risk assessed (destructive actions, sensitive-data exposure, external transmission, privilege changes, irreversible operations) and explaining the policy tiers and workspace_root risk. This goes beyond the annotations.

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 a single sentence that is information-dense and well-structured. It front-loads the core purpose and then lists covered aspects, with no redundant filler. Every clause contributes value.

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?

The tool is complex with nested objects and an output schema, but the description covers the purpose, decision types, policy modes, and risk factors. It gives the agent enough to understand when and how to use it, and the output schema explains return values. The description is complete for the tool's complexity.

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 description coverage is 100%, so the baseline is 3. The description repeats some parameter details (policy levels, workspace_root) but adds no new meaning beyond the schema. It does not compensate for any gaps because there are none.

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 tool's function: analyzing a proposed AI-agent tool call before execution and returning a decision. It specifies the resource (tool call), the action (analyze), and the output (allow/notice/confirm/block), distinguishing it from sibling tools like inspect_file or analyze_url_risk which target different resource 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 'before execution,' indicating when to use the tool. It also describes the policies and risk factors, giving clear context. However, it does not explicitly mention when not to use it or name alternatives, though sibling names imply a division of labor.

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

All Agent Utility MCP 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

A4.2/5.0

Disambiguation4/5

Each tool targets a distinct input type (tool call, URL, command, file), but analyze_tool_call could overlap with inspect_command when the tool call is a shell command. Descriptions are specific enough to mostly disambiguate.

Naming Consistency4/5

All tools follow a verb_noun pattern, but they mix 'analyze_' and 'inspect_' as verbs. The structure is consistent across tools, though the verb choice is not uniform.

Tool Count5/5

Four tools covering the core analysis targets (action, URL, command, file) is well-scoped for a security-analysis utility, not too thin and not overbuilt.

Completeness4/5

The surface covers the main entities an agent would need to analyze, but there are minor gaps such as a tool for managing policies or analyzing other data types (e.g., IP addresses or free-form text).

Resources

Need Help?