QuerySail: Google Search Console

Compare Search Console performance

compare_performance

Read-onlyIdempotent

Use this when the user asks what changed between two periods, why traffic went up or down, or which pages, queries, countries or devices gained or lost. Compares clicks, impressions, CTR and average position for one property between a current period and the previous period (default), the same weekdays a year earlier, or explicit dates. Returns both totals with absolute and percent changes, the click change split into an impressions part and a CTR part, and, with a dimension, the top gainers and losers ranked by change in clicks or impressions. Dates are Pacific Time; with no dates the current period is the last 28 finalized days. Filters and search type apply to both periods. Changes are observed differences and do not identify causes. Read-only; does not change anything in Search Console.

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": {
      "property_id": "<property_id>"
    },
    "name": "compare_performance"
  }
}

Input Schema

Name	Required	Description
`movers`	No	Gainers and losers to return each. Default 10, maximum 50.
`filters`	No	Applied to both periods, combined with AND. Same format as get_performance filters.
`rank_by`	No	Rank movers by change in clicks (default) or impressions.
`end_date`	No	Current period end, YYYY-MM-DD (Pacific Time). Provide together with start_date.
`dimension`	No	Optional breakdown for top gainers and losers. Omit for totals only.
`compare_to`	No	'previous_period' (default) is the same number of days immediately before; 'previous_year' is 52 weeks earlier, so weekdays line up. Not used with explicit previous dates.
`data_state`	No	'final' (default) uses finalized data only; 'all' includes recent preliminary days.
`start_date`	No	Current period start, YYYY-MM-DD (Pacific Time). Provide together with end_date.
`property_id`	Yes	Exact property ID from list_properties, e.g. 'sc-domain:example.com' or 'https://example.com/'.
`search_type`	No	Which results to compare. Default 'web'. discover and googleNews have no queries.
`connection_id`	No	Optional: force a specific Google connection when the property is visible to several.
`previous_end_date`	No	Optional explicit comparison period end, YYYY-MM-DD.
`previous_start_date`	No	Optional explicit comparison period start, YYYY-MM-DD. Must end before the current period starts.

Output Schema

Name	Required	Description	Default
`notes`	No
`units`	No
`losers`	No
`totals`	No
`gainers`	No
`request`	No
`coverage`	No
`property`	No
`freshness`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 11, 2026
- removedOutput schema / properties / requestId
```
Removed value: -{
-  "type": "string"
-}
```
First observedOct 6, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the description is not required to restate safety. It goes well beyond that, disclosing timezone (Pacific), the default window (last 28 finalized days), that filters and search type apply to both periods, and that the click change is decomposed into an impressions part and a CTR part. It also sets expectations about causality, which is meaningful behavioral context for an analytics tool.

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?

The use-case trigger is front-loaded, followed by scope, then mechanics, then caveats, which is a sound ordering. A few phrases, such as the closing read-only sentence, are redundant with annotations and could be trimmed. Overall it is dense but nearly every sentence carries information.

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?

For a 13-parameter analytical tool with an output schema, the description covers the decision-relevant facts: default windows, timezone, cross-period filter behavior, comparison-mode options, and the shape of the result. It does not need to re-document return fields because an output schema exists, and nothing an agent needs in order to call this correctly appears to be missing.

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 still adds value by explaining the semantics of the comparison modes (default previous period, same weekdays a year earlier, explicit dates) and by clarifying that the dimension parameter governs the gainers/losers breakdown rather than the totals. This is a modest but real lift over the schema.

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 states a specific verb (compares), an object (clicks, impressions, CTR, average position for one property between two periods), and the dual output modes (totals vs. per-dimension gainers/losers). It is clearly distinguishable from get_performance, which presumably returns a single-period dataset rather than a period-over-period comparison.

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 gives concrete triggers: 'what changed between two periods, why traffic went up or down, or which pages, queries, countries or devices gained or lost.' It also warns that changes are observed differences and do not identify causes, which heads off a misuse. It stops short of naming a sibling alternative explicitly, so it lands at 4 rather than 5.

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

All QuerySail: Google Search Console 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.