delete_dns_subdomain

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

The description adds an auth prerequisite not present in the annotations ('Требует права pdns/edit') and explicitly flags destructiveness with 'ДЕСТРУКТИВНО', reinforcing destructiveHint=true in natural language that an agent will weight heavily. It is fully consistent with annotations (readOnlyHint=false, destructiveHint=true), so no contradiction exists. It does not, however, describe irreversibility or potential cascade effects on related DNS records.

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?

Three short clauses totaling about ten words front-load the action, then the destructiveness warning, then the permission requirement. Every clause earns its place and there is no filler or repetition.

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 simple 3-parameter destructive delete with full schema documentation and matching annotations, the essential calling conditions are covered: purpose, destructiveness, permission prerequisite, and the required confirm flag (via schema). Minor gaps remain — no error behavior, no response shape (no output schema exists), and no disclosure of side effects despite openWorldHint=true — but nothing an agent needs to invoke 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%, with all three parameters (id, confirm, server_id) already documented in the input schema, so the baseline of 3 applies. The description adds no parameter-level detail — it only restates the object being deleted. The confirm-flag requirement is left entirely 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?

The description opens with a specific verb and resource — 'Удалить сабдомен из таблицы сабдоменов' (delete subdomain from the subdomains table) — and even references the internal endpoint (pdns/delete_subdomain). This clearly distinguishes it from sibling tools like delete_dns_domain, delete_dns_record, and delete_dns_zone, which act on different resource types.

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?

The phrase 'из таблицы сабдоменов' implies this is the subdomain-level deletion tool, which gives contextual differentiation from domain/record/zone siblings, but no alternative is named and no explicit when/when-not conditions are given. The permission note 'Требует права pdns/edit' states a precondition but does not guide tool selection.

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