Skip to main content
Glama

Read site health

readSiteHealth
Read-onlyIdempotent

What Kooga's crawl of the site found, from the newest audit: its score (0 to 100, higher is healthier), how many pages it checked, the site-wide checks (robots.txt, sitemap, llms.txt, whether AI crawlers may read the site, which structured data the pages carry), and every kind of issue with what it means, how many pages have it and a few of them, worst first. schedule says when the next crawl runs. audit is null when the site was never crawled. These are the site's own pages, not rankings or AI visibility.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "readSiteHealth"
  }
}

Input Schema

NameRequiredDescriptionDefault
workspaceIdNoThe workspace, as listWorkspaces gives it (its id or slug). Leave it out when this connection reaches one workspace.

Output Schema

NameRequiredDescriptionDefault
siteYes
auditYes
countsYesIssues by severity, counted per page
issuesYes
scheduleYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / site / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "aiCrawlersAllowed": {
      -        "description": "Whether robots.txt lets AI crawlers read the site; null when it could not be read",
      -        "type": [
      -          "boolean",
      -          "null"
      -        ]
      -      },
      -      "llmsTxt": {
      -        "type": [
      -          "boolean",
      -          "null"
      -        ]
      -      },
      -      "robotsTxt": {
      -        "type": [
      -          "boolean",
      -          "null"
      -        ]
      -      },
      -      "sitemap": {
      -        "type": [
      -          "boolean",
      -          "null"
      -        ]
      -      },
      -      "structuredData": {
      -        "anyOf": [
      -          {
      -            "additionalProperties": false,
      -            "properties": {
      -              "article": {
      -                "type": "boolean"
      -              },
      -              "faq": {
      -                "type": "boolean"
      -              },
      -              "organization": {
      -                "type": "boolean"
      -              },
      -              "product": {
      -                "type": "boolean"
      -              },
      -              "website": {
      -                "type": "boolean"
      -              }
      -            },
      -            "required": [
      -              "product",
      -              "article",
      -              "organization",
      -              "website",
      -              "faq"
      -            ],
      -            "type": "object"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ],
      -        "description": "Which structured data types the pages read carry"
      -      },
      -      "url": {
      -        "type": [
      -          "string",
      -          "null"
      -        ]
      -      }
      -    },
      -    "required": [
      -      "url",
      -      "robotsTxt",
      -      "sitemap",
      -      "llmsTxt",
      -      "aiCrawlersAllowed",
      -      "structuredData"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "aiAccess": {
      +        "anyOf": [
      +          {
      +            "additionalProperties": false,
      +            "properties": {
      +              "challenged": {
      +                "description": "A page answered with a bot challenge instead of itself",
      +                "type": "boolean"
      +              },
      +              "emptyPages": {
      +                "description": "Pages with no readable text before JavaScript runs",
      +                "items": {
      +                  "type": "string"
      +                },
      +                "type": "array"
      +              },
      +              "pages": {
      +                "type": "integer"
      +              },
      +              "unpricedPages": {
      +                "description": "Product pages with no price in their HTML",
      +                "items": {
      +                  "type": "string"
      +                },
      +                "type": "array"
      +              }
      +            },
      +            "required": [
      +              "pages",
      +              "challenged",
      +              "emptyPages",
      +              "unpricedPages"
      +            ],
      +            "type": "object"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "description": "What a crawler running no JavaScript got from the key pages"
      +      },
      +      "aiCrawlersAllowed": {
      +        "description": "Whether robots.txt lets search and answer bots read the site; null when it could not be read",
      +        "type": [
      +          "boolean",
      +          "null"
      +        ]
      +      },
      +      "llmsTxt": {
      +        "type": [
      +          "boolean",
      +          "null"
      +        ]
      +      },
      +      "robotsTxt": {
      +        "type": [
      +          "boolean",
      +          "null"
      +        ]
      +      },
      +      "sitemap": {
      +        "type": [
      +          "boolean",
      +          "null"
      +        ]
      +      },
      +      "structuredData": {
      +        "anyOf": [
      +          {
      +            "additionalProperties": false,
      +            "properties": {
      +              "article": {
      +                "type": "boolean"
      +              },
      +              "faq": {
      +                "type": "boolean"
      +              },
      +              "organization": {
      +                "type": "boolean"
      +              },
      +              "product": {
      +                "type": "boolean"
      +              },
      +              "website": {
      +                "type": "boolean"
      +              }
      +            },
      +            "required": [
      +              "product",
      +              "article",
      +              "organization",
      +              "website",
      +              "faq"
      +            ],
      +            "type": "object"
      +          },
      +          {
      +            "type": "null"
      +          }
      +        ],
      +        "description": "Which structured data types the pages read carry"
      +      },
      +      "url": {
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      }
      +    },
      +    "required": [
      +      "url",
      +      "robotsTxt",
      +      "sitemap",
      +      "llmsTxt",
      +      "aiCrawlersAllowed",
      +      "aiAccess",
      +      "structuredData"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  2. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: only the newest audit is returned, `audit` is null for never-crawled sites, issues are ordered worst-first, and `schedule` reports the next crawl. It does not address pagination or truncation, and since it is a read with a single optional param that reliance on annotations is reasonable — a 3 rather than higher because no operational caveats (rate limits, freshness lag beyond 'newest audit') are given.

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?

Content is front-loaded: the resource and score semantics come first, then the enumerated checks, then the edge case (`audit` null) and the scope exclusion last. The middle sentence is a dense run-on enumeration, but every clause carries selection-relevant information rather than padding.

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 needn't explain return shapes — yet it does so usefully to support tool selection. The one gap is the null-audit path: it says `audit` is null but not what an agent should do next (e.g., a sibling/flow that triggers a crawl), which matters because it is the only non-happy path.

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% and the sole parameter (workspaceId) is already documented in the schema, including the 'leave it out for single-workspace connections' rule. The description never mentions workspaceId, so it adds no meaning beyond the schema. Baseline 3 applies.

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 pins down the exact resource ('Kooga's crawl of the site... from the newest audit') and enumerates the payload — score, pages checked, site-wide checks, issue list, schedule — so an agent knows precisely what it gets before calling. It also draws a hard scope line ('These are the site's own pages, not rankings or AI visibility'), which separates it from the many read* analytics siblings such as readRankings or readPerformance.

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?

Context for when to reach for it is clear: it is the newest audit snapshot, 'audit is null when the site was never crawled', and it is explicitly not the rankings/AI-visibility surface. What is missing is routing to a concrete alternative — it never names a sibling to call instead when audit is null or when the caller actually wants rankings.

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