Skip to main content
Glama
Suganthan-Mohanadasan

Google Search Console MCP Server

by Suganthan-Mohanadasan
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

compare_web_vs_image

Identify queries where image search drives disproportionate impressions compared to web by comparing side-by-side performance metrics for each query.

Instructions

For each query, returns side-by-side performance across web and image search. Two GSC API calls joined on query, with an impressions ratio that surfaces where image search carries disproportionate volume relative to web. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables. POSITION: position is an impression-weighted average over real impressions, blended across queries, devices and countries. It is not a rank-tracker rank. Deep positions are only recorded when a user actually reaches that part of the results, so values beyond page one rest on sparse data. Treat absolute positions as directional and prefer position deltas between periods when judging change.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
daysNoNumber of days to analyse
site_urlNoOverride the configured property (e.g. sc-domain:example.com or https://www.example.com/)
row_limitNoMaximum rows to return
min_combined_impressionsNoMinimum combined (web + image) impressions to include the query

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.5.1
    • addedInput schema / properties / site_url
      Added value: +{
+  "description": "Override the configured property (e.g. sc-domain:example.com or https://www.example.com/)",
+  "type": "string"
+}
  2. Addedv2.4.0

TDQS

A4.2/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and exceeds it: it discloses the two-call join implementation, mandates evidence-only analysis with exact numbers and no speculation, requires a specific interactive dashboard presentation, and explains the non-obvious position metric semantics (impression-weighted, not rank-tracker, sparse deep data, prefer deltas). This is rich behavioral context far beyond generic annotations.

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 core function is front-loaded in the first sentence, and each subsequent block earns its place: analysis guardrails prevent hallucinated causes, presentation rules standardize output in the absence of an output schema, and the position caveat prevents metric misinterpretation. The length (~230 words) is justified given zero annotations and no output schema.

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 tool with no annotations and no output schema, this is unusually complete: data source, join method, analysis constraints, presentation format, and metric interpretation are all covered. The remaining gap is that the exact set of returned fields (e.g., whether clicks and CTR are included per search type) is never enumerated, leaving the agent to infer the output structure from 'side-by-side performance' and 'impressions ratio.'

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% (all four parameters documented with defaults and examples), so the baseline is 3. The description adds no parameter-specific meaning beyond the schema; its discussion of impressions ratio and position concerns output interpretation rather than parameter usage. It neither harms nor enhances parameter understanding.

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 opening sentence states a specific verb and resource: 'returns side-by-side performance across web and image search,' and adds methodological detail ('Two GSC API calls joined on query, with an impressions ratio'). This clearly differentiates it from the many image-only siblings (image_keyword_overview, image_search_quick_wins, etc.), since no other sibling compares web versus image search.

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 purpose statement implies the use case (comparing web vs image performance per query), but the description never explicitly says when to choose this tool over alternatives or when not to use it. With 20+ overlapping GSC siblings, explicit routing like 'for image-only analysis use image_keyword_overview' would materially help. The IMPORTANT/PRESENTATION/POSITION sections govern post-invocation behavior, not tool selection.

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

Deploy Server

Other Tools