Gia hạn tên miền (trừ ví VND)

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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true. The description goes well beyond: it discloses that dry_run=false deducts the VND wallet, that the renewal is executed at the registrar, that 502 means funds are held pending reconciliation (explaining the non-idempotent hint), and that repeated retries are harmful. No contradiction with annotations.

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?

Front-loaded with purpose, then the mandatory call sequence, then the two error branches. Dense but every clause is actionable (price source, approval gate, wallet debit, error routing); there is 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 non-idempotent money-spending mutation with no output schema, the description covers the full lifecycle an agent needs: the dry-run/confirm/commit sequence, the returned price_vnd, wallet deduction, and both failure paths. Nothing required to call it safely is missing.

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 100%, so id, dry_run, and billing_cycle are already documented in the schema. The description restates dry_run's pricing behavior (VAT-inclusive) and the safety default, but adds little parameter-level meaning the schema does not already provide; the workflow sequencing it adds is usage guidance rather than parameter semantics. Baseline 3 is appropriate.

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+resource ('Gia hạn tên miền' - renew domain) and scopes it to domains bought via MONA Cloud, which cleanly separates it from cloud_domain_buy, cloud_domain_list, and the DNS/NS siblings. An agent knows immediately what operation this performs.

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?

Gives an explicit two-call workflow (always dry_run=true first, ask user to approve the price, then dry_run=false) plus named error branches: 402 routes to cloud_topup with QR, and 502 tells the agent to stop retrying and inform the user. This is prescriptive when-to-use guidance with alternatives and exclusions.

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