Расчёт по выгрузке

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, covering the safety profile. The description adds valuable behavior: 'Gaps do not become zeros' and 'calculation concerns only the saved WB page'. These go beyond annotations and help the agent understand edge-case handling.

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?

Three sentences, each carrying distinct information: the core operation, the field specification mechanism, and two behavioral constraints. Front-loaded and no redundancy.

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 tool with nested objects and no output schema, the description provides general purpose and key behaviors but omits details about required parameters like `arrayPointer` and `resultId`, and the semantics of filter operators and metric ops are left to the schema. Adequate for a simple tool but incomplete for this complexity.

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 0%, so the description must compensate for the five parameters. It explains that fields are specified by JSON Pointer, which clarifies `field` values, but it does not explain `arrayPointer`, `resultId`, or the structure of the `metrics` array and `filter` object. The compensation is inadequate for a nested schema.

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 clearly states the tool computes local sums, averages, grouping, and filtering on a saved result. The verb 'aggregate' is implied through these operations, and the resource (saved WB page) is identified. However, it does not explicitly contrast with siblings like wb_read or wb_result, so it misses full differentiation.

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 implies usage for aggregation on a saved WB page and notes the constraint 'only saved page' but offers no explicit guidance on when to use this tool versus alternatives like wb_read or wb_result. There are no exclusions or alternative routing.

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