Mencoro

Apply a proposed clustering

apply_auto_clustering

Apply the grouping a completed start_auto_clustering job proposed: creates the clusters it named and moves the tracked queries into them, as the job's mode said. Cluster names are lower-cased like create_clusters, and a proposed name that matches an existing cluster reuses it instead of creating a second one. Show the proposal (get_job) to the user first. Pass a fresh requestId and reuse it if you retry, so a retry never applies twice.

Input Schema

TableJSON Schema

Name	Required	Description
`jobId`	Yes
`projectId`	Yes
`requestId`	No	Optional idempotency key, 8-255 printable characters. Reuse it only to retry this same call.
`organizationId`	Yes

Output Schema

TableJSON Schema

Name	Required	Description
`failed`	No	Always present, empty list included: read it rather than inferring success from the status code.
`clusters`	No	Every cluster the assignments referred to, and whether this call created it.
`successful`	No	Tracked queries written, each with the cluster ids it ended up with - the resulting state, not the delta.
`unassigned`	No	Tracked queries the job produced no assignment for. Nothing was written for them and they keep the clusters they already had, under every merge mode.
`skippedClusters`	No	Proposed names the store cannot hold. A tracked query whose proposed cluster was skipped ends up with fewer clusters than the proposal showed.

Schema Changelog

Changes observed during successful MCP inspections.

AddedSep 28, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations only declare the safety profile (readOnly=false, destructive=false, idempotent=false); the description goes further by disclosing the actual side effects (creates clusters, moves tracked queries), name normalization, existing-cluster reuse instead of duplication, and idempotency behavior via requestId. This is meaningful behavioral context an agent cannot derive from the annotations alone.

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?

Four sentences, each carrying distinct information (action, naming/reuse rule, preview prerequisite, idempotency key). The main action is front-loaded and there is no filler or repetition of the title.

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 multi-step, stateful mutation the description covers the prerequisite (view proposal), the side effects, the naming/reuse semantics, and the retry/idempotency contract. An output schema exists, so return values need not be explained. Nothing needed to invoke it correctly is 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 only 25%, so the description must compensate. It fully explains the non-obvious requestId (fresh key, reuse only on retry) and ties jobId to the start_auto_clustering job, but organizationId and projectId are left to inference. Strong on the parameter that matters, silent on the trivial ones.

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?

States a specific verb and resource ('Apply the grouping a completed start_auto_clustering job proposed') and explicitly names the producer sibling (start_auto_clustering), the naming convention shared with create_clusters, and the preview tool (get_job). An agent can distinguish this from create_clusters, start_auto_clustering, and set_tracked_query_clusters without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit workflow guidance: show the proposal via get_job first, and only apply after. It also names the retry condition ('reuse it if you retry'), routing the agent correctly between generating a proposal, previewing it, and applying it.

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

All Mencoro 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.