Sync Yandex Direct statistics by pulling campaign, spend, and conversion data from the provider module and saving normalized records to local SQLite for analysis.
Read Yandex Direct statistics through the provider MCP module and persist normalized campaigns, spend and conversions into local SQLite.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | ||
| from | No | ||
| currency | No | ||
| module_id | No | ||
| tool_name | No | ||
| project_id | No | ||
| campaign_ids | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It does disclose that data is normalized and written to local SQLite, which is useful, but it says nothing about whether the write overwrites, upserts or appends, whether it requires a configured module, or what permissions/auth are needed.
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 that states the read and the write in one pass with no filler. It is efficient, though extremely short relative to a 7-parameter 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?
For a mutating tool with no annotations, no output schema, and seven entirely undocumented parameters, the description is far too thin. An agent cannot determine required identifiers, idempotency behavior, or what the persisted output looks like without guessing.
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?
Seven parameters with 0% schema description coverage, and the description only loosely maps to a few of them (date range via 'statistics', 'campaigns' and spend/conversions). The critical module_id, tool_name and project_id parameters — likely required to actually route the call — are entirely unexplained.
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 names a specific verb pair (read + persist) and a concrete resource (Yandex Direct statistics), and adds the destination (local SQLite). It differentiates itself from the pure-read sibling ads_yandex_direct_report by stating that it persists normalized data, though it never names that sibling explicitly.
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?
Usage is only implied: the word 'persist' suggests this is the tool to use when you want the data stored locally rather than just viewed. There is no explicit statement of when to prefer this over ads_yandex_direct_report or when a sync is appropriate versus unnecessary.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.