Skip to main content
Glama

aribot

by io.github.aristiun
OverviewDiscussionsAdmin

Apply a remediation (governed)

apply_remediation
Destructive

Apply a remediation for real (mode=live). Goes through Aribot's governance checks (attack-path reachability, autonomy policy and the approval flow). If your policy requires approval it returns 'requires_approval' rather than acting.

Input Schema

NameRequiredDescriptionDefault
rule_idYesPolicy/rule id (e.g. AWS_S3_PUBLIC_ACCESS)
threat_idYesThreat id/code to remediate
resource_contextYesThe cloud resource: provider, resource_id (required), region, account_id, metadata

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / resource_context / description
      Previous value: -"provider/resource_id/region/account_id/metadata"New value: +"The cloud resource: provider, resource_id (required), region, account_id, metadata"
    • changedInput schema / required
      Previous value: -[
-  "threat_id",
-  "rule_id"
-]New value: +[
+  "threat_id",
+  "rule_id",
+  "resource_context"
+]
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=true, so the safety profile is covered. The description adds real value on top: it names the governance gates (attack-path reachability, autonomy policy, approval flow) and discloses the 'requires_approval' no-op outcome, telling the agent it won't always mutate. It could go further on reversibility/scope but this is solid.

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?

Three tight sentences with the core 'act for real' fact front-loaded, then the governance path, then the failure outcome. No filler; each sentence carries a distinct point.

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?

For a governed mutation with no output schema, the description covers the key behavioral facts an agent needs: it acts live, it passes governance, and it may return 'requires_approval'. Naming the read sibling would close the last gap, but nothing essential is missing to invoke it correctly.

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% with all three required parameters documented (including the nested resource_context members). The description adds no parameter-level detail, so the schema does the work; baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Apply a remediation for real') and the '(mode=live)' qualifier signals it performs the actual write, implicitly contrasting with a preview/read counterpart. It does not name the sibling get_remediation explicitly, so it's just short of full differentiation, but an agent can still tell this apart from the read side.

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

Usage Guidelines3/5

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

It sets the context (governance checks, approval flow) and the outcome when approval is needed, which implies when it will act versus defer. However, it never explicitly routes the agent from alternatives like get_remediation or states when-not-to-use, leaving the choice to inference.

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

All aribot toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources