Изменить объект (общий)

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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) by disclosing the dry-run-by-default safety gate, the re-read verification step and the all-or-nothing success criterion after write. The "change only the fields you specified" warning and the banking-document exclusion add real mutation semantics. Minor gap: no mention of required permissions or rate/timeout behavior at the description level.

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?

Densely packed but front-loaded: purpose and mechanism first, then dry-run/confirm, then the safety caveat and exclusion. Every sentence carries information, though the prose is compact enough that the field-naming hint and the exclusion slightly compete for attention. No filler.

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 5-parameter, nested-object, open-world mutation tool with an output schema and full annotation coverage, the description covers purpose, workflow, safety and exclusions adequately. The operationId/retry protocol lives in the confirm parameter description rather than the tool description, which is acceptable given the output schema exists, but the description never notes that the response includes such a preview handle.

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 coverage is 100%, so the baseline is 3, but the description adds meaning on top: technical field names must be discovered via describe_entity, with a concrete payload example ({"ИНН":"7701234567"}) that illustrates the fields object shape. It also foregrounds the default dry-run behavior of confirm. It does not explain entitySet allowed values beyond the schema example.

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?

States a specific verb and resource ("Изменяет произвольные поля объекта 1С через PATCH по Ref_Key") and clearly delimits scope: only the fields passed are touched. It also names the sibling it is not used for (bank document contract/settlement settings), so an agent can distinguish it from the many write.* siblings without opening schemas.

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?

Explicit workflow: look up technical field names via describe_entity first, default call is a dry-run, apply with confirm=true. It also names an exclusion with the exact alternative tool (write.document.apply_bank_settlement_settings), which is the strongest form of when-not-to-use guidance.

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