Mencoro

Create a project

create_project

Create a project that monitors a brand: its website domains, the brand names to look for, and optionally its competitors. Tracked queries are added afterwards with create_tracked_queries. Before calling it, propose everything to the user at once: brand names from suggest_brand_names, and competitors from discover_competitors (poll get_job; each comes with its website and names); if that job is refused, fails or finds none, competitors you suggest with their websites instead (suggest_brand_names finds the names each one goes by), without holding up the setup. Pass the chosen competitors here: one added later only counts in checks from then on. After the first checks, list_untracked_competitors shows other brands the answers name. Pass a fresh requestId and reuse it if you retry, so a retry never creates a second project. Refused to a member restricted to selected projects.

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": {
      "organizationId": "<organizationId>",
      "name": "<name>",
      "websiteDomains": "<websiteDomains>",
      "brandNames": "<brandNames>"
    },
    "name": "create_project"
  }
}

Input Schema

Name	Required	Description
`name`	Yes
`requestId`	No	Optional idempotency key, 8-255 printable characters. Reuse it only to retry this same call.
`brandNames`	Yes	The names the brand is mentioned by, e.g. ["Acme", "Acme Corp"]
`competitors`	No
`organizationId`	Yes
`websiteDomains`	Yes	The brand's own domains, e.g. ["acme.com"]

Output Schema

Name	Required	Description
`id`	Yes
`name`	Yes
`status`	Yes
`createdAt`	Yes
`brandNames`	Yes	Brand names matched in AI answers and search results. Empty when the project has no brand monitoring profile yet.
`competitors`	Yes	Competitors this project is measured against. Empty when none are configured.
`organizationId`	Yes
`websiteDomains`	Yes	Domains the project is monitored for. Empty when the project has no brand monitoring profile yet.

Schema Changelog

Changes observed during successful MCP inspections.

AddedSep 28, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well past the annotations by disclosing that competitors passed at creation count in checks immediately while 'one added later only counts in checks from then on', that the call is refused for members restricted to selected projects, and how requestId prevents a retry from creating a second project. The idempotency guidance is consistent with idempotentHint=false because it explains how to manufacture idempotency via the key rather than claiming the call is inherently idempotent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and every block is relevant, but the middle section is a very long, clause-heavy sentence ('if that job is refused, fails or finds none, competitors you suggest with their websites instead (suggest_brand_names finds the names each one goes by), without holding up the setup') that is hard to parse on first read. The content earns its place but the packaging does not.

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?

For a 6-parameter creation tool with an output schema, this covers the workflow, idempotency, late-competitor semantics, and access restrictions, which is close to everything an agent needs to call it correctly. The only notable omission is any description of organizationId, which an agent must infer from context.

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?

With only 50% schema description coverage, the description usefully explains that each competitor 'comes with its website and names', that suggested competitors should be passed with their websites, and how to use requestId ('fresh requestId and reuse it if you retry'). organizationId is never described and the expected shape of the nested competitor objects is left to the schema, so the compensation is good but not complete.

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?

Opens with a specific verb and resource plus its scope: 'Create a project that monitors a brand: its website domains, the brand names to look for, and optionally its competitors.' It also distinguishes itself from the tracked-query tooling by stating that queries are added afterwards with create_tracked_queries, so an agent can place it among the siblings without opening a 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?

Explicitly prescribes the sequence around the call: gather brand names from suggest_brand_names, competitors from discover_competitors (poll get_job), and fall back to self-suggested competitors if that job is refused, fails, or finds none. It also names the follow-on tool list_untracked_competitors for after the first checks and states when the call is refused, which is unusually complete when-to-use and when-blocked guidance.

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.