Continuous agent-speed defense for public surfaces

exposure_verdict

Scoped diff verdict for one of your verified surfaces (trial or subscription; the $25 one-off rail is the HTTP /verdict endpoint).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "surface_id": "<surface_id>"
    },
    "name": "exposure_verdict"
  }
}

Input Schema

Name	Required	Description	Default
`surface_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

C2.7/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden, and it largely fails: it doesn't state whether this is read-only or a mutation, what the verdict contains, what permissions or billing state it requires beyond rail type, or any rate limits. The rail-scoping note is the only behavioral context added.

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?

A single front-loaded sentence with no padding. It is dense with parenthetical jargon, but every clause (rail scope, alternative endpoint) carries signal rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and 0% parameter coverage, the description is the only source of truth and leaves major gaps: what a 'verdict' returns, whether the call is safe/read-only, and how to supply surface_id. It is materially under-specified for a callable tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for the single required surface_id parameter. It only implies that surface_id refers to 'one of your verified surfaces' — it gives no format, sourcing, or example, leaving the agent to guess how to obtain and shape the value.

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

Purpose3/5

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

The description names a specific resource ('one of your verified surfaces') and a concrete artifact type ('scoped diff verdict'), so the agent knows it operates per-surface. However, 'verdict' is jargon that doesn't clarify what the tool actually computes or returns, and it doesn't distinguish itself from the sibling defense_verdicts. Purpose is only partially recoverable.

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?

The parenthetical gives a real routing hint: this applies to trial/subscription rails, while the $25 one-off rail should use the HTTP /verdict endpoint instead. That is a genuine when-not signal. It still says nothing about when to prefer this over defense_run or defense_verdicts.

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

All Continuous agent-speed defense for public surfaces tools Inspect

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

Need Help?