Skip to main content
Glama

Ground Truth - Fresh Evidence for AI Agents

by io.github.anish632

Security Header Inspection

inspect_security_headers
Read-onlyIdempotent

Inspect security-related HTTP response headers for an unfamiliar public URL before an agent trusts or recommends it. It identifies missing or weak HSTS, CSP, framing, referrer, permissions, and cross-origin headers. It reports observable configuration only and does not prove that a site is secure or vulnerability-free.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesPublic http(s) URL or bare domain to inspect. Bare domains are normalized to https:// automatically.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesNormalized URL that was fetched.
errorNoValidation or network error when the request could not be completed.
httpsYesTrue when the normalized URL used https.
scoreNoHeuristic security-header score based on how many tracked headers were present.
statusNoHTTP status code returned by the endpoint.
headersNoTracked response headers and their raw values when present.
summaryYesShort human-readable explanation of the verdict.
verdictYesHeader preflight verdict based on reachability, HTTPS, and tracked header presence.
evidenceYesStructured header observations used to produce the verdict.
inputUrlNoOriginal user input when normalization changed it.
next_stepYesAgent-readable follow-up for sources that should be checked repeatedly.
accessibleYesTrue when the endpoint returned an HTTP response.
presentCountNoNumber of tracked security headers that were present.
missingRecommendedNoTracked headers that were not present on the response.
recommended_actionYesSuggested next step; not a security guarantee.

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering basic safety. The description adds meaningful context by noting it 'reports observable configuration only and does not prove that a site is secure or vulnerability-free', which sets expectations for result interpretation. It also enumerates header types checked.

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 three sentences that are tightly scoped: purpose, usage context, and a crucial caveat. Each sentence adds distinct value with zero redundancy or filler, and the most important information is front-loaded.

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?

With annotations covering safety and an output schema present, the description adequately covers purpose, usage timing, limitations, and parameter handling. A minor gap is that it does not explicitly state that a live network request is made, but openWorldHint already implies external resource access.

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?

The schema description already fully covers the single parameter: 'Public http(s) URL or bare domain to inspect. Bare domains are normalized to https:// automatically.' Since schema coverage is 100%, the description adds no additional parameter meaning, warranting the baseline score of 3.

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 states a specific verb ('Inspect') with a clear resource ('security-related HTTP response headers') and a specific context ('for an unfamiliar public URL before an agent trusts or recommends it'). The focus on security headers and trust/recommendation clearly distinguishes it from sibling tools like check_endpoint or verify_claim.

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?

It provides a clear usage context by specifying 'before an agent trusts or recommends it' and cautions that it 'does not prove that a site is secure or vulnerability-free', which helps agents decide when to rely on results. However, it does not explicitly name alternative tools or state when not to use it.

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

All Ground Truth - Fresh Evidence for AI Agents toolsInspect
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

A4.3/5.0
Disambiguation4/5

Most tools have clearly distinct purposes, but there are several lightly overlapping pairs (check_endpoint/preflight_endpoint, check_pricing/compare_pricing_pages, estimate_market/compare_competitors, test_hypothesis/verify_claim). The detailed descriptions and explicit 'do not use for' notes mitigate confusion, so misselection is unlikely.

Naming Consistency5/5

All tool names follow a consistent lowercase snake_case verb_noun pattern (e.g., check_endpoint, create_monitor, verify_claim). Even compound verbs like preflight_endpoint and run_monitor_now adhere to the same structure, making the naming fully predictable.

Tool Count4/5

19 tools is slightly heavy but reasonable for the broad scope covering endpoint checks, pricing, compliance, package research, claim verification, and monitor lifecycle. Each tool has a distinct role, though the count edges close to the 'heavy' range.

Completeness4/5

Core workflows are well-covered: create/list/delete/get/run/preview monitors, single and comparative pricing checks, endpoint and security verification, and claim testing. Minor gaps exist, such as no update_monitor tool or a way to explicitly verify a claim without pre-supplied evidence URLs, but these are workable.

Resources