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

Goes well beyond the readOnly/idempotent annotations: it discloses the per-row metrics (opens, unique browsers, visits with at least one answer, completed visits), the null-row semantics, the separate empty-string row for by=param, sort order (descending opens, null last), the 200-row cap with truncated=true, and the important edge case that anonymous-answer quizzes return empty device/browser/country breakdowns. These are exactly the behaviors an agent cannot infer from annotations or schema.

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?

Front-loads the core operation and dimensions, then layers output semantics, limits, and cross-references in a sensible order. The text is dense and long but nearly every clause carries actionable information; the hidden_options parenthetical is the one slightly noisy aside.

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 6-parameter read-only aggregation with no output schema, the description covers output shape, ordering, truncation, null handling, and the anonymous-quiz edge case, which is what an agent needs to interpret results. The remaining details (date format, enum values) are fully handled by the 100%-covered schema.

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 coverage is 100% and each parameter already carries its own description, so the schema does the heavy lifting (baseline 3). The description only reinforces that by=param needs key and explains what null/empty values mean in the output; it adds no new syntax or constraint detail for by, key, device, or the date range.

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?

Opens with a specific verb and resource: 'Разбивает посещения опроса ... по одному признаку' and enumerates the four dimensions (link param value, device, browser, country). This is clearly distinguishable from the sibling get_quiz_visits, which returns the raw visits rather than an aggregation.

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 description makes clear this is a one-dimensional breakdown and routes the agent to sibling tools for the parameter names it needs (get_quiz_report filters.extra_fields, get_quiz_variables on any plan), and warns that quiz://{id}/hidden_options does not contain them. It does not explicitly contrast with get_quiz_visits for the non-aggregated case, so the when-not guidance is implied rather than stated.

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