Skip to main content
Glama

Organiq GEO

by com.organiqgeo
OverviewDiscussionsAdmin

Query shapes (incl. AI-style)

analyze_query_shapes
Read-onlyIdempotent

Classifies the period's queries into shapes and aggregates each: branded, question, comparison, transactional, local, longtail (5+ words), head (<= 2 words), other, with queries, clicks, impressions, ctr, position, shares, comparison (clicksChangePct, impressionSharePoints) and top example queries per shape. Also reports the "AI-style" split used by the Organiq dashboard (conversational marker or >= 5 words: the kind of query AI Overviews / AI Mode answer) — a proxy, since Search Console does not expose AI-feature data in the API. Shapes: branded = contains one of the property's branded terms; question = interrogative (how, what, why, como, o que, qual…); comparison = compares options (vs, best, melhor, diferença entre…); transactional = buying intent (price, buy, comprar, preço, promoção…); local = local intent (near me, perto de mim, address…); longtail = 5+ words without another marker; head = 2 words or fewer; other = 3–4 words without a marker. Use for intent mix, "how much of our demand is questions", GEO (generative engine) planning. / Formatos de query (perguntas, comparação, transacional, marca, longas "estilo IA") com shares e exemplos.

Input Schema

NameRequiredDescriptionDefault
daysNoWindow length in days (default 28). Ignored when startDate and endDate are both given. / Janela em dias.
siteYesProperty: displayName ("example.com"), Search Console siteUrl ("sc-domain:example.com", "https://www.example.com/") or numeric id. A unique substring among visible properties also works ("exam"). list_sites shows the options. / Propriedade por nome, siteUrl ou id.
brandNoall (default); branded = only queries containing one of the property's branded_terms; non-branded = the rest. Needs branded terms set on the property in the Organiq panel, otherwise invalid_argument with the panel URL. / Marca × sem marca.
queryNoOnly queries containing this text, or a regex as /…/ (e.g. "/^how to/"; no flag = case-insensitive).
deviceNoDevice.
compareNoComparison: previous (default) = same-length window immediately before; year = same dates one year earlier; none. / Comparação.
countryNoCountry as ISO-3166-1 alpha-3, as in Search Console: bra, usa, prt, arg.
endDateNoEnd yyyy-mm-dd. Default: last synced date of the property (Search Console lags ~3 days; never "today"). Every response states the period used. / Fim; padrão = última data sincronizada.
examplesNoExample queries per shape (default 3).
startDateNoStart yyyy-mm-dd. Default: endDate − (days − 1).
searchTypeNoSearch type (default web).
pageContainsNoOnly pages whose URL contains this text (case-insensitive), e.g. "/blog/".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive, closed-world, so the safety profile is handled. The description adds genuine non-obvious context: the 'AI-style' split is an explicit proxy because Search Console does not expose AI-feature data via the API, which prevents an agent from over-claiming it as real AI Overview data.

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?

It is front-loaded with the purpose and almost every clause earns its place, since the shape definitions are needed to interpret the output. The weakness is structural: the first sentence is a dense multi-parenthetical run-on that mixes the return payload, shape thresholds and the AI proxy into one block, making it harder to scan than it needs to be.

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?

With 12 parameters, no output schema and a non-obvious classification scheme, the description carries the full burden of explaining the return values, and it does: metrics, comparison fields, per-shape examples, and the exact rule for each shape. Nothing an agent needs in order to call or interpret this tool is missing.

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% and every parameter is already documented, including the branded-terms prerequisite on `brand` and the `examples` default. The description restates output aggregation and shape rules rather than adding parameter-level meaning, so it lands at the baseline of 3.

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 opening states a specific verb and resource ('Classifies the period's queries into shapes and aggregates each') and then enumerates both the shapes and the metrics returned, so an agent knows exactly what comes back. It is not differentiated by name from its closest sibling (get_query_shape_trend for trends, get_longtail_clusters for clustering), but the shape taxonomy is detailed enough that the boundary is inferable.

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 use cases ('intent mix', 'how much of our demand is questions', GEO planning), which is real routing guidance beyond the name. It stops short of explicit exclusions or naming alternatives like get_query_shape_trend for the time dimension, so the agent must infer when another shape tool is preferable.

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

All Organiq GEO 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