Create a label in Yandex Metrika to categorize and organize your counters, goals, and filters. Use the Management API to add a new label with a specified name.
https://yandex.ru/dev/metrika/ru/management/ Create label. Body: {"label": {"name": "..."}}
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes | JSON request body. For POST/PUT use the structure from API docs (e.g. {"counter": {...}}). | |
| pretty | No | Pretty-print response (1) |
Changes observed during successful MCP inspections.
v0.2.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden of behavioral disclosure. It only says 'Create label' and shows the body format; it does not mention persistence, side effects, authorization needs, idempotency, or response behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and front-loaded, with the key body shape included immediately. The documentation URL is low-value noise, but it does not prevent the description from being quickly scannable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, the description should clarify what happens when a label is created, such as the expected response, success behavior, or failure conditions. It provides a minimal body example but omits these operational details, making it only partially complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema's body description is generic, but the tool description adds the label-specific body structure `{"label": {"name": "..."}}`, which is meaningful and helps an agent construct a valid call. The other parameter, `pretty`, is already documented in the schema, and schema coverage is 100%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the operation clearly with 'Create label' and provides the exact body shape, so an agent knows it creates a label resource. It does not explain what a label is or explicitly distinguish itself from the many sibling label tools beyond the verb, which prevents a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance about when to use this tool instead of mgmt_label_update, mgmt_label_delete, or other management tools. The intended use is only implied by the name and one-word description, so the agent must infer usage from context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.