metrika_get_statistics

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

The description declares 'read-only' and 'bounded', which gives some safety and limit information, but it is minimal. With no annotations provided, the description carries the full burden of disclosure. It fails to mention what happens on errors, whether authentication is required, what rate limits apply, or what the response structure looks like. The term 'bounded' is ambiguous—it could mean limited result size, request throttling, or something else.

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 one short sentence, which is technically concise, but it is under-specified rather than efficiently informative. It fails to convey essential usage details, so the brevity works against usefulness. A concise description would include the key elements of what the tool does and how to use it; this omits nearly all of them.

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 reporting tool with an open 'params' object and an output schema (which suggests a rich response), the description is grossly incomplete. An agent would not know what to put in the params, what the response contains, or what 'bounded' means in practice. The tool is not callable correctly based on this description alone. Even with an output schema, the input side is entirely unspecified.

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 schema has a single required parameter 'params' which is an open object with additionalProperties: true and no property definitions. Schema description coverage is 0%. The description adds no information about what keys this object should contain, such as counter ID, date range, metrics, or filters. An agent has zero guidance on how to construct the request body, making this parameter effectively opaque.

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 identifies the tool as a 'Metrika reporting request' with a specific verb ('run') and resource ('Metrika reporting'), which separates it from a pure tautology. However, it is vague about what 'statistics' actually means—no mention of metrics, dimensions, date ranges, or counters. It does not differentiate itself from sibling tools like metrika_list_counters or direct_get_statistics beyond the name, leaving an agent to guess the exact scope.

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?

No guidance is provided on when to use this tool versus alternatives. The description does not mention any conditions, prerequisites, or exclusions, nor does it reference sibling tools like metrika_list_goals or direct_get_statistics. An agent has no contextual hints about the appropriate use case.

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