Mark

Get Search Performance

get_search_performance

Read-onlyIdempotent

Reports Google Search Console results (queries, pages, clicks, impressions, position), including striking distance queries (positions 5–20) and anomalies. The text repeats totals and the top 10 pages, queries, striking distance rows and anomalies as markdown and as a fenced JSON block. Pass compareFrom and compareTo for prior-period totals. performance.daily, totals and dataThrough are Google's final data only; performance.preliminary has the newer days Google may still revise, the same shape as daily, never in daily or totals. The default period ends 3 days ago, so preliminary is usually empty; pass to as today's date for Google's newer days. Requires a connected Search Console property. Related: inspect_url, list_saved_keywords.

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": "get_search_performance"
  }
}

Input Schema

Name	Required	Description
`to`	No	Range end YYYY-MM-DD.
`from`	No	Range start YYYY-MM-DD. Defaults to the last 28 settled days.
`compareTo`	No	Prior period end YYYY-MM-DD. Requires compareFrom.
`compareFrom`	No	Prior period start YYYY-MM-DD. Requires compareTo.

Output Schema

Name	Required	Description	Default
`appUrl`	Yes
`exceptions`	Yes
`performance`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 7, 2026

addedInput schema / properties / compareFrom

Added value: +{
+  "description": "Prior period start YYYY-MM-DD. Requires compareTo.",
+  "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
+  "type": "string"
+}

addedInput schema / properties / compareTo

Added value: +{
+  "description": "Prior period end YYYY-MM-DD. Requires compareFrom.",
+  "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
+  "type": "string"
+}

First observedOct 1, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the read-only/idempotent annotations, it discloses prerequisites (a connected Search Console property), the response packaging (totals and top-10 rows repeated as markdown and as a fenced JSON block), and the crucial data-freshness semantics: daily/totals/dataThrough are final-only while preliminary holds newer revisable days never included in daily or totals. That is exactly the non-obvious behavior an agent cannot infer elsewhere.

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?

Front-loaded with purpose, then freshness semantics, then alternatives—logical ordering with no filler sentences. The preliminary-versus-final explanation is restated twice (once in the schema of the data, once as the 'default period ends 3 days ago' note), a minor redundancy that costs it the top mark.

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?

An output schema exists, yet the description still usefully covers the text-rendering duplication and the preliminary/final split that the schema alone would not convey, plus the authentication prerequisite. For a four-parameter read tool, an agent has everything needed to call it and interpret the result correctly.

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 goes beyond it by explaining what compareFrom/compareTo actually do (prior-period totals) and by tying the `to` parameter to a real consequence—whether preliminary data appears at all. It does not add formatting caveats beyond the schema's YYYY-MM-DD pattern, but the added meaning is genuine.

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: reports Google Search Console results, enumerating the dimensions returned (queries, pages, clicks, impressions, position) plus striking distance rows and anomalies. The GSC-specific scope distinguishes it from analytics-style siblings such as get_performance_overview or get_ga4_organic_overview without needing to open a schema.

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 concrete conditional guidance: pass compareFrom/compareTo for prior-period totals, and pass `to` as today's date to obtain Google's newer, still-revisable days rather than the default settled range. It does not explicitly say when to choose this tool over the similarly named overview/content performance siblings, so it stops short of full routing guidance.

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

All Mark tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?