Skip to main content
Glama

Client: split searches, titles not clicked, near-wins and lost pages from Search Console

gsc_insights
Read-onlyIdempotent

What a client's Search Console data says, worked out the same way every time: searches split between two of the site's pages (with the page that should win), page-one results that get far fewer clicks than their position should (rewrite the title and description), searches sitting just off the top (positions 4–15, the cheapest wins), pages that lost clicks against the period before with the searches they lost, and how much of the search traffic is the business's own name. Read this before changing titles, merging pages or picking the next page to work on.

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": {
      "client": "<client>"
    },
    "name": "gsc_insights"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoLength of each period compared (default 28)
clientYesClient name from list_clients

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds beyond that: it is deterministic ("worked out the same way every time") and discloses the analytical categories returned even without an output schema, including the prior-period comparison. It doesn't discuss auth or rate limits, but the key behavioral value is present.

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?

Two sentences, the first front-loading the determinism claim before the output list, the second stating the use case. The five-item enumeration is dense but each item earns its place by naming a distinct analysis; no filler.

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 no output schema, the description carries the return-value burden and does so by listing the five result categories an agent will receive. For a two-parameter read-only analytics tool this is largely sufficient; only exact response shape/formatting is left unstated.

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 coverage is 100%, so both `client` and `days` are documented in the schema. The description indirectly reinforces `days` by describing loss "against the period before," implying two compared periods, but adds no syntax or constraint detail beyond the schema. Baseline 3 is appropriate.

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 names the resource (a client's Search Console data) and enumerates the five specific analyses produced: split searches, under-clicked page-one titles, near-wins at positions 4–15, lost pages vs. prior period, and branded-traffic share. This is far more specific than the name alone, though it never names the sibling it is not (e.g., gsc_query for raw pulls), leaving differentiation implicit.

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?

"Read this before changing titles, merging pages or picking the next page to work on" gives clear when-to-use conditions tied to concrete tasks. It lacks any when-not or explicit alternative (such as gsc_query for ad-hoc metrics), 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.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.