Прочитать точную настройку счетов расчётов

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

Annotations already declare readOnlyHint=true, so the read-only nature is covered, but the description adds real behavioral context: inherited settings are not substituted, an empty organization GUID means all organizations in counterparty/group mode, and a missing or incompatible schema blocks the call. That last point in particular is non-obvious operational risk information not present in the structured fields.

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 sentences are dense but front-loaded, leading with what is read and immediately qualifying it with the no-inheritance rule. The final note about the legacy name is useful disambiguation rather than filler, though the reference to a 'scope' field with no matching parameter costs some clarity.

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?

With annotations covering safety and an output schema covering return values, the description only needs to explain mode selection and constraints, which it largely does. The remaining gap is that the mode-selection logic is expressed via an abstract 'scope' rather than the actual contractRef-emptiness rule an agent must apply.

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 20% (only 'database' is documented), so the description must carry the load. It does clarify contractRef (omit it for counterparty/group mode) and organizationRef (empty GUID = all organizations), but it gives no guidance on the three settlementKind enum values or on the counterpartyRef vs group distinction beyond the vague 'в том же поле Контрагент_Key'.

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 names a concrete verb and resource ('Читает точную настройку независимого регистра') and signals that inherited settings are NOT substituted, which implicitly contrasts with the sibling get_settlement_settings. It stops short of explicitly naming that sibling or stating the distinguishing rule outright.

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?

It explains how the mode is derived (contract vs counterparty/group based on whether a contract is supplied) and that organization and settlement kind are mandatory, which is genuine usage context. However, it frames this around a 'scope' concept that does not exist as a parameter in the schema, and it never explicitly says when to prefer this over read.accounting.get_settlement_settings.

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