Skip to main content
Glama

Audit public site

audit_public_site
Read-onlyIdempotent

Use this for a bounded, sitemap-first audit of a public website the user owns or is authorized to inspect. It fetches at most 8 same-origin HTML pages per call, respects robots.txt, and returns compact page summaries plus deduplicated findings and a sampled cross-page canonical/noindex/hreflang evidence graph. It does not recursively follow HTML links, authenticate, execute JavaScript, fetch assets, or run site-wide link checks. To continue a batch, pass both the returned page offset and discovery fingerprint; changed sitemaps require restarting at offset 0.

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": {
      "site_url": "<site_url>"
    },
    "name": "audit_public_site"
  }
}

Input Schema

NameRequiredDescriptionDefault
site_urlYesAuthorized public website URL. The final public origin becomes the crawl boundary.
max_pagesNoMaximum same-origin pages to audit in this call, from 1 to 8.
page_offsetNoZero-based sitemap-page offset for continuing a capped audit batch.
expected_discovery_fingerprintNoFingerprint from the first batch. Required when page_offset > 0 to reject sitemap drift.

Output Schema

NameRequiredDescriptionDefault
errorNo
pagesYes
overviewYes
site_urlYes
discoveryYes
truncatedYes
sitemap_urlNo
issue_groupsYes
pages_failedYes
pages_auditedYes
pages_partialYes
pages_selectedYes
discovery_errorNo
next_page_offsetNo
pages_discoveredYes
audit_health_scoreNo
indexability_graphNo
pages_skipped_robotsYes
discovery_fingerprintYes
issue_groups_truncatedYes
score_coverage_percentYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / properties / expected_discovery_fingerprint
      Added value: +{
      +  "description": "Fingerprint from the first batch. Required when page_offset > 0 to reject sitemap drift.",
      +  "pattern": "^[a-f0-9]{64}$",
      +  "type": "string"
      +}
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • changedOutput schema / properties / discovery_error / enum
      Previous value: -[
      -  "robots_unavailable",
      -  "sitemap_unavailable",
      -  "sitemap_invalid"
      -]New value: +[
      +  "robots_unavailable",
      +  "sitemap_unavailable",
      +  "sitemap_invalid",
      +  "sitemap_query_unsupported"
      +]
    • addedOutput schema / properties / discovery_fingerprint
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / indexability_graph
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "coverage_limited": {
      +      "type": "boolean"
      +    },
      +    "findings": {
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "code": {
      +            "type": "string"
      +          },
      +          "confidence": {
      +            "enum": [
      +              "observed",
      +              "potential"
      +            ],
      +            "type": "string"
      +          },
      +          "example_urls": {
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "message": {
      +            "type": "string"
      +          },
      +          "severity": {
      +            "enum": [
      +              "error",
      +              "warning",
      +              "info"
      +            ],
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "code",
      +          "severity",
      +          "confidence",
      +          "message",
      +          "example_urls"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "findings_truncated": {
      +      "type": "boolean"
      +    },
      +    "limitations": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "sampled_pages": {
      +      "maximum": 9007199254740991,
      +      "minimum": 0,
      +      "type": "integer"
      +    },
      +    "scope": {
      +      "const": "sampled_pages_only",
      +      "type": "string"
      +    },
      +    "sitemap_pages_sampled": {
      +      "maximum": 9007199254740991,
      +      "minimum": 0,
      +      "type": "integer"
      +    }
      +  },
      +  "required": [
      +    "scope",
      +    "sampled_pages",
      +    "sitemap_pages_sampled",
      +    "coverage_limited",
      +    "limitations",
      +    "findings",
      +    "findings_truncated"
      +  ],
      +  "type": "object"
      +}
    • addedOutput schema / properties / issue_groups / items / properties / code
      Added value: +{
      +  "description": "Stable machine-readable audit rule identifier when available.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / pages / items / properties / indexability
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "canonical_state": {
      +      "enum": [
      +        "missing",
      +        "usable",
      +        "ambiguous",
      +        "unverifiable"
      +      ],
      +      "type": "string"
      +    },
      +    "canonical_url": {
      +      "type": "string"
      +    },
      +    "hreflang": {
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "language": {
      +            "type": "string"
      +          },
      +          "url": {
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "language",
      +          "url"
      +        ],
      +        "type": "object"
      +      },
      +      "maxItems": 16,
      +      "type": "array"
      +    },
      +    "hreflang_truncated": {
      +      "type": "boolean"
      +    },
      +    "noindex_observed": {
      +      "type": "boolean"
      +    },
      +    "title": {
      +      "maxLength": 150,
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "canonical_state",
      +    "noindex_observed",
      +    "hreflang",
      +    "hreflang_truncated"
      +  ],
      +  "type": "object"
      +}
    • addedOutput schema / properties / pages / items / properties / top_findings / items / properties / code
      Added value: +{
      +  "description": "Stable machine-readable audit rule identifier when available.",
      +  "type": "string"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "site_url",
      -  "discovery",
      -  "pages_discovered",
      -  "pages_selected",
      -  "pages_audited",
      -  "pages_partial",
      -  "pages_failed",
      -  "pages_skipped_robots",
      -  "truncated",
      -  "score_coverage_percent",
      -  "pages",
      -  "issue_groups",
      -  "issue_groups_truncated",
      -  "overview"
      -]New value: +[
      +  "site_url",
      +  "discovery",
      +  "pages_discovered",
      +  "pages_selected",
      +  "pages_audited",
      +  "pages_partial",
      +  "pages_failed",
      +  "pages_skipped_robots",
      +  "truncated",
      +  "discovery_fingerprint",
      +  "score_coverage_percent",
      +  "pages",
      +  "issue_groups",
      +  "issue_groups_truncated",
      +  "overview"
      +]
  2. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior; the description adds substantive context beyond that: an 8-page cap, robots.txt compliance, no recursion/auth/JS/asset fetching, and fingerprint-based rejection of sitemap drift that forces a restart at offset 0.

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?

Four dense sentences, front-loaded with purpose then hard limits then batch mechanics, with no redundant restatement of the name or title.

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?

For a four-parameter tool with annotations and an output schema, the description covers the authorization precondition, crawl boundary, per-call cap, and pagination contract, so nothing an agent needs to invoke and continue it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns above that by explaining the coupling between page_offset and expected_discovery_fingerprint and the restart-at-zero failure mode, which the schema fields do not convey on their own.

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?

States a specific verb and resource with scope modifiers: 'bounded, sitemap-first audit of a public website the user owns or is authorized to inspect.' The negative clause ('does not recursively follow HTML links... or run site-wide link checks') separates it from crawling and link-checking siblings.

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?

Gives explicit qualifying context (public site the user owns or is authorized to inspect) and a clear continuation procedure for batches. It does not name an alternative sibling or state when to choose audit_public_webpage or check_broken_links instead, relying on exclusions to steer.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources