Расход ИИ

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so safety is covered structurally. The description adds real context beyond that: the filter values must match keys returned in a prior response and may include deleted connections, which warns the agent about value provenance. It still omits anything about auth needs, rate limits, or result size.

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?

Two tight sentences, front-loaded with what the report contains and followed by the critical value-provenance constraint. No filler, though the second clause is dense and slightly cryptic without the prior-response context.

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 read-only report with no output schema, the description usefully enumerates the report's sections (totals, comparison, days, breakdowns), which partially stands in for a return-shape spec. But with 5 of 6 parameters undocumented in the schema and only a partial description of the filter values, the definition leaves the agent short on how to call it correctly.

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 only 17% (only 'case' is documented), so the description must compensate. It partially does by explaining that provider, bot, kind and model are exact keys from the previous response's choices (including deleted connections), giving their valid domain. The 'days' parameter and the schema's case semantics remain unexplained by the description.

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 states a specific deliverable: a full usage report ('Полный отчёт расхода') with totals, comparison, per-day data and breakdowns. This is clearly a reporting/read tool and is easily distinguished from the ai_list/ai_save/ai_delete/ai_test siblings. It does not, however, explicitly name or contrast with a sibling.

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?

There is no explicit statement of when to use this tool versus alternatives such as ai_list or ai_test. The only usage-shaped hint is that provider/bot/kind/model must be exact keys from a previous response, which is a data-sourcing note rather than selection guidance.

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