wb_nm_report

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

With no annotations, the description carries the full behavioral burden and discloses three genuinely operational traits: the report is task-based (asynchronous), the call waits up to 3 minutes, and results are retained for 3 days. This meaningfully informs the agent about latency and caching expectations. It stops short of covering timeout behavior and read-only confirmation, but the disclosed traits are material and non-obvious.

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 dense sentence where every clause earns its place: scope, metrics, async nature, wait time, and retention policy. The core purpose is front-loaded ahead of operational detail, with zero filler words.

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 task-based report with no annotations and no output schema, the description covers the report contents and the async lifecycle, which is good. However, it leaves meaningful gaps: what happens if the task exceeds 3 minutes, whether nm_ids or date bounds are effectively required, timezone semantics for the date strings, and the response shape. Adequate for an agent to attempt the call, but not fully 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?

Schema coverage is 67%, but the schema descriptions are thin ('filter' for nm_ids, only a format for date_from, nothing for date_to). The description adds meaning by establishing nm_ids as the report's subject scope, the date fields as the reporting window, and the metrics returned. It does not state value formats, bounds, count limits, or whether any parameter is effectively required, so it only partially compensates for the schema's weak coverage.

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?

States a specific scope — 'Per-nmID report' — and enumerates the contained metrics: revenue, orders, returns, conversions. This is sufficient to distinguish it from sibling report tools by content focus, though the verb is implied rather than explicit and no sibling is named for contrast. The Russian parenthetical 'отчёт по номенклатуре' reinforces the nomenclature 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 given on when to use this tool versus the many report siblings (wb_search_report, wb_finance_report, wb_stats_sales, wb_analytics_detail, wb_goods_return_report). The agent is left to infer from the name alone that this is the per-nomenclature reporting variant, and there is no when-not-to-use or alternative routing information.

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