Skip to main content
Glama
AKzar1el

Google Search Console MCP

Compare Performance Between Periods

analytics.compare
Read-only

Compare Search Console clicks, impressions, CTR, and average position between two date ranges for a chosen dimension (query, page, country, device). Identifies performance shifts and flags data limits.

Instructions

Compare Search Console performance metrics (clicks, impressions, CTR, average position) between two distinct date ranges (Period A vs Period B) for a selected dimension (query, page, country, device). Pagination metadata flags when either period reached the local 100,000-row safety ceiling; Search Console itself may still return only top data.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
site_urlYesThe Search Console property identifier, exactly as returned by sites.list. Two formats exist: domain properties use 'sc-domain:example.com'; URL-prefix properties use the full URL including protocol and trailing slash, e.g. 'https://www.example.com/'. Passing the wrong format returns a permission error even when the user owns the site — call sites.list first if unsure.
dimensionNoThe dimension to compare performance for. Defaults to query.query
end_date_aYesEnd date of Period A (recent, YYYY-MM-DD)
end_date_bYesEnd date of Period B (previous, YYYY-MM-DD)
start_date_aYesStart date of Period A (recent, YYYY-MM-DD)
start_date_bYesStart date of Period B (previous, YYYY-MM-DD)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
paginationYes
comparisonsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the readOnlyHint annotation, the description adds valuable behavioral details about pagination metadata and the 100,000-row safety ceiling, plus the caveat that Search Console may still return only top data. This discloses limitations and external behavior without contradicting any 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?

Two sentences with no filler: the first delivers the main purpose, metrics, and dimension options; the second front-loads the pagination caveat. Every sentence earns its place and the most important behavior is highlighted early.

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?

The description covers purpose, supported dimensions, and a key behavioral limitation. An output schema exists for return format, annotations cover read-only safety, and the schema documents parameter details, so nothing essential an agent needs to call this correctly is missing.

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 input schema already describes all 6 parameters with coverage at 100%, including date formats, dimension enum, and site_url format details. The description only restates the dimension list and period comparison, adding no new parameter-level meaning beyond the schema baseline.

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 uses a specific verb ('Compare') and names the exact resource ('Search Console performance metrics') with concrete metrics and dimensions. It clearly distinguishes this from the sibling 'analytics.query' by emphasizing comparison across two distinct date ranges rather than a single period.

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?

The description clearly states the context for use: comparing performance between two date ranges for a selected dimension. It does not explicitly name alternatives or provide when-not-to-use guidance, but the comparison purpose is unambiguous enough to imply selection over a single-period query.

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