Skip to main content
Glama

Inspect edge headers

inspect_edge

Read response headers from an allowlisted endpoint to report its TLS-terminating PoP, clarifying edge-plane location only - it never establishes where inference ran.

Instructions

Read response headers from an ENTITLED endpoint only (config.json allowlist) and report the TLS-terminating PoP. Explicitly an edge-plane fact: it never establishes where inference ran.

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": {
      "url": "<url>"
    },
    "name": "inspect_edge"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesURL of an endpoint the fleet is entitled to call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations at all, the description carries the full burden and does fairly well: 'Read' signals a non-mutating operation, the allowlist clause discloses an authorization/entitlement prerequisite, and the closing sentence explicitly bounds the epistemic scope of the result. It omits what happens on a non-entitled URL (error shape) and any rate-limit or caching behavior.

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?

Two tight sentences, front-loaded with the action and constraint, ending on the caveat that prevents the most likely misinterpretation. Nothing is padded and no sentence is redundant.

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 one-parameter, no-output-schema, no-annotation tool this covers most of what an agent needs: what is read, what is reported, and what conclusion must not be drawn. The absence of any output schema means the description could have said more about the returned header set, but the essentials are present.

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% for the single 'url' parameter, so the baseline is 3. The description's 'ENTITLED endpoint only (config.json allowlist)' adds a little context about the allowlist source, but the schema already says 'an endpoint the fleet is entitled to call', so the marginal value is small.

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 ('Read response headers') and a specific resource ('an ENTITLED endpoint'), plus the derived fact it reports (the TLS-terminating PoP). It also delimits scope by denying an inference-location interpretation, though it never names the sibling tool that does answer that question.

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 gives a hard precondition ('config.json allowlist') and an implicit when-not ('it never establishes where inference ran'), which steers the agent away from misusing it. However, it never names an alternative tool or states a positive use case beyond the mechanics, so routing guidance is only implied.

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