Skip to main content
Glama
Sign In

mowteng

by app.mowteng
OverviewDiscussionsAdmin

Query Google search performance

gsc_search_analytics
Read-only

Google clicks, impressions, CTR (0-1) and average position for a property, grouped by the chosen dimensions. Returns up to rowLimit rows (at most 1,000 per call); when more may exist, next_start_row is set for the next page. The insights_* tools compute common analyses over all rows.

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": {
      "siteUrl": "<siteUrl>",
      "startDate": "<startDate>",
      "endDate": "<endDate>"
    },
    "name": "gsc_search_analytics"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoSearch type. Defaults to web.
endDateYesEnd date, YYYY-MM-DD
filtersNoFilters, all of which must match
siteUrlYesSearch Console property exactly as gsc_list_sites returns it: "https://example.com/" or "sc-domain:example.com"
rowLimitNoMaximum rows (1-1,000). Defaults to 100.
startRowNoZero-based row to start from, for paging. Defaults to 0.
dataStateNofinal (default), all to include fresh data, or hourly_all together with the hour dimension
startDateYesStart date, YYYY-MM-DD
dimensionsNoGroup rows by these dimensions. Omit for site totals.
aggregationTypeNoHow to aggregate. Defaults to auto.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description focuses instead on pagination behavior: the 1,000-row cap and the fact that next_start_row signals more data exists. That is genuine operational context an agent cannot get from the annotations. It omits any note on data-freshness latency or quota behavior, which would matter for a reporting API.

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 tight sentences front-load the return payload, then pagination, then the sibling escape hatch. No filler and no restatement of the name or 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?

With 10 parameters and no output schema, the description carries the burden of explaining returns, and it does name the metric fields and the paging cursor. The main residual gap is that it never explains what happens with aggregationType or multi-dimension grouping, which are non-obvious for a 10-parameter query tool.

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%, so the schema already explains dates, filters, dimensions, and limits, making 3 the baseline. The description adds only the rowLimit ceiling and the CTR 0-1 scale (an output detail), without clarifying semantics of aggregationType, dataState, or dimension combinations beyond what the schema states.

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 first sentence names the exact metrics returned (clicks, impressions, CTR, average position) and the resource (a Search Console property, grouped by chosen dimensions), which is far more specific than the title. It does not explicitly distinguish itself from the close sibling gsc_performance_overview, which an agent could easily confuse with this row-level query.

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?

It names an alternative family ('The insights_* tools compute common analyses over all rows'), giving the agent a clear reason to pick those when precomputed analyses are wanted and this tool when raw grouped rows are wanted. It stops short of explicit when-not conditions (e.g. vs gsc_performance_overview) and gives no prerequisite guidance beyond the schema.

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

All mowteng toolsInspect
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