Сохранить точную настройку счетов расчётов

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses that when DataVersion is absent and singleWriter is used, If-Match is not sent and there is no atomic protection against concurrent changes. It also lists the validations performed (organization, IsFolder, no deletion; contract owner, organization, currency) and notes that the preview is tied to the current record. It does not describe the response shape or failure modes, but it discloses the key behavioral traits the annotations omit.

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?

It is a single dense paragraph with no filler, and the create/update distinction plus the concurrency rule are front-loaded. The parenthetical asides and long clauses make it hard to scan, but nearly every sentence carries decision-relevant information.

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?

Given a 12-parameter mutation tool with a nested accounts object and an output schema, the description covers the confirm flow, concurrency handling, scope branches, validation behavior, and the hard limits on global settings and deletion. What remains missing is the meaning of the individual account slots and settlementKind values, which the agent must infer from the schema alone.

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 25% across 12 parameters, so the description must compensate, and it does for the hardest ones: mode, scope, contractRef, expectedDataVersion, singleWriter, and operationId semantics are all explained. It leaves the accounts sub-object fields, settlementKind values, and database/organizationRef/counterpartyRef meanings to the schema, so gaps remain but the critical conditional parameters are covered.

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 verb pair and resource: it creates a missing settlement-account setting (create) or changes explicitly listed resources (update), and it names the scope variants (contract/counterparty/group). It also distinguishes the legacy name set_contract_settlement_settings, which only supports contracts. It does not explicitly contrast with the nearby siblings apply_bank_settlement_settings or get_settlement_settings, so sibling differentiation is partial rather than complete.

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 states the required flow: preview first, then confirm with the same arguments plus the operationId from the preview. It states the branch conditions explicitly: expectedDataVersion with If-Match when DataVersion is published, and singleWriter=true only when metadata lacks DataVersion. It also states that scope=contract requires contractRef while counterparty/group do not, and that global settings and deletion are unavailable.

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