Resolve uncertain Yandex Metrika management writes by reading provider state to confirm results. Use an idempotency key and never resend the operation.
Settle an uncertain Metrika management write by reading the provider; never resends.
| Name | Required | Description | Default |
|---|---|---|---|
| args | No | ||
| operation | Yes | ||
| idempotency_key | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.7.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare idempotentHint=true, destructiveHint=false and openWorldHint=true, so much of the safety profile is structured. The description does add a trait beyond the annotations: reconciliation is achieved 'by reading the provider' and the tool 'never resends' the write, clarifying the mechanism. It still says nothing about required auth, rate limits, or what state it mutates when the provider read disagrees.
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?
A single front-loaded sentence with no padding; the mechanism ('by reading the provider') and the key guarantee ('never resends') come before anything else. Efficient, though arguably under-developed for a three-parameter management tool.
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?
An output schema exists so return values need not be explained, but the definition omits the two required parameters' meaning, the valid 'operation' values, and how this fits with metrika_manage_prepare/apply. For a write-family reconciliation tool with 0% schema coverage, that leaves the agent guessing at invocation.
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?
Schema description coverage is 0% across three parameters, and the description never mentions 'operation', 'idempotency_key' or 'args'. 'never resends' gestures at idempotency semantics but gives no key format, no valid operation values, and no explanation of when args are needed — the description fails to compensate for the coverage gap.
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 verb+resource combination ('Settle an uncertain Metrika management write') is specific and places the tool in the prepare/apply/reconcile family alongside metrika_manage_read, metrika_manage_prepare and metrika_manage_apply. An agent can tell it apart from the read/prepare/apply siblings without opening the schema, though 'settle' is slightly jargon-y.
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?
The trigger condition is implied ('an uncertain Metrika management write'), so an agent can infer this runs after an apply whose outcome is unknown. However, no sibling is named as the alternative and there is no explicit when-not-to-use guidance (e.g. 'do not use for a fresh write — use metrika_manage_apply').
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.