Skip to main content
Glama

Search Console performance

search_console_performance
Read-only

Retrieve organic Google Search clicks, impressions, CTR and average position grouped by query, page, country, device or date; filter results and set a date window to analyze search performance.

Instructions

Organic Google Search clicks, impressions, CTR and average position for a website, grouped by query, page, country, device or date, most clicks first. Search Console's last 2-3 days are incomplete, so the window ends 3 days ago unless fresh is set. Group by query and page together to see whether several pages compete for the same search; by page and date to see when a page's impressions or position changed. Changes nothing.

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": "search_console_performance"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoLook-back window in days, ending 3 days ago (yesterday with fresh)
freshNoInclude the last 2-3 days, which Google is still filling in (they read low). Use to check something from the last few days
limitNoMost rows to return
end_dateNoExact last day, YYYY-MM-DD
site_urlYesSearch Console property exactly as search_console_sites lists it, e.g. sc-domain:example.com or https://www.example.com/
dimensionsNoWhat to group by
page_regexNoOnly pages whose URL matches this RE2 regex
start_dateNoExact first day, YYYY-MM-DD
query_regexNoOnly queries matching this RE2 regex
page_containsNoOnly pages whose URL contains this text
query_containsNoOnly queries containing this text
exclude_query_regexNoLeave out queries matching this RE2 regex, typically the brand name, e.g. (?i)acme|ac me

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.46.0
    • changedInput schema / properties / start_date / description
      Previous value: -"Exact first day, YYYY-MM-DD. Pass with end_date to use exact dates instead of days"New value: +"Exact first day, YYYY-MM-DD"
  2. First observedv0.11.0

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description still adds real context the annotations cannot: Search Console's last 2-3 days are incomplete so the window ends 3 days ago unless fresh is set, and the default ordering is by clicks descending. It does not discuss result caps, row limits or quota behavior, so the disclosure is useful but not complete for a 12-parameter tool.

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?

Three sentences, front-loaded with the metrics and dimensions, then the data-latency caveat, then the analytical use cases. No filler and no restatement of the name or title.

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 12-parameter read tool with no output schema, the definition covers what is returned (four metrics), how it is grouped and ordered, and the key data-availability caveat. Remaining gaps, such as row limits and regex filter behavior, are handled by the fully documented schema, so the description is close to complete without being exhaustive.

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 description coverage is 100%, so the baseline is 3. The description earns a bump by explaining the semantics of dimension combinations (query+page, page+date), which the schema only lists as enum values, and by restating the fresh/window interaction that governs days and end_date. It does not cover the regex filters or limit behavior, but those are well documented in the schema itself.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a concrete verb-and-resource statement: it returns organic Google Search clicks, impressions, CTR and average position for a site, grouped by query/page/country/device/date and sorted by clicks. It also closes with "Changes nothing," which separates it from the propose_* siblings. It stops short of naming a specific sibling to route against, so an agent must infer the boundary with search_console_trend or search_console_summary.

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?

Guidance is genuinely actionable: combine query+page to spot pages competing for the same search, and page+date to see when impressions or position shifted. The fresh-flag caveat also carries an implicit when-to-use (checking the last few days). There is no explicit when-not or named alternative, which keeps it from a 5.

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