Пакетное создание

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

Annotations indicate openWorldHint=true, so no contradiction. The description adds behavioral details: it creates records (mutating), uses batch semantics, automatically resolves lookup fields, and supports continue_on_error. This goes beyond annotation information.

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 a single sentence that packs essential information without redundancy. All three sentences (or clauses) are non-repetitive and earn their place.

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?

No output schema and no description of return values (e.g., success status, error details). Could also mention permissions or side effects. While core behavior is covered, missing return information reduces completeness for a batch operation.

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 description adds meaning for two of three parameters: records (explains lookup resolution) and continue_on_error (explained as skipping errors). Collection is not elaborated. Schema coverage is 67% but description compensates for the key param behaviors.

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 creates multiple records in a single batch, specifies OData v4, and mentions key features like automatic lookup resolution and continue_on_error. It effectively distinguishes from sibling tools such as bpm_create_record (single record) and bpm_batch_update/delete (different operations).

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 mentions 'только OData v4', which hints at prerequisite, but does not explicitly state when to use this tool vs. alternatives (e.g., when batch is appropriate over individual creates). No exclusions or when-not-to-use guidance provided.

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