Подготовить безопасную запись Kwork

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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=true): it discloses the pre-flight account binding check, action-specific preflight, payload_hash/TTL/HMAC confirmation_token return, that only the token hash is persisted in the ledger, exact-replay idempotency semantics, and that a different request under the same key is rejected. This is exactly the behavioral context an agent needs for a two-phase write.

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?

Dense but well front-loaded: the core purpose and the no-side-effect guard lead, then actions, then the token/replay mechanics. Every sentence carries weight, though the ledger/replay detail is slightly heavy for a description whose return shape is also documented by the output schema.

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?

An output schema exists, so return values need not be spelled out, yet the description still summarizes them (payload_hash, TTL, confirmation_token). For an 8-action, single-entry-point write tool, the coverage of preflight, idempotency, and confirmation flow is sufficient for correct invocation.

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 carry the load. It lists the actions that the `request` oneOf accepts (matching the schema's const variants) and gives real semantic content for `idempotency_key` (exact replay returns the same token; conflicting reuse is forbidden), compensating for the missing per-field documentation, though per-field meaning of price/duration/metrics is still left to the 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?

States a specific verb and resource ('проверить и сохранить точный Kwork write payload') plus the crucial scope qualifier 'без remote side effect', which distinguishes it from the committing sibling commit_write without needing to open either schema. It enumerates the 8 supported actions so the agent immediately knows the surface area.

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?

Usage is implied rather than stated: 'без remote side effect' and the token/TTL/ledger flow signal this is the safe first step of a prepare→commit sequence, but the description never names commit_write, get_write_status or reconcile_write as the follow-up tools, nor states when-not to use this. Inference is required.

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