Create or replace a zone profile

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

Discloses the critical behavioral trait beyond annotations: replacing is 'in its entirety' and 'Records absent from the submitted document are dropped' — a direct data-loss warning an agent must know before invoking. It also states the return value and interacts well with openWorldHint=true, where the get-first advice mitigates the risk of dropping records the agent doesn't know about. No conflict with readOnlyHint=false; destructiveHint=false is consistent with save-not-delete semantics while the description still surfaces the destructive nuance.

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 dense sentences front-load the core action, follow with the most dangerous consequence (dropped records), and close with workflow routing. Every sentence earns its place; roughly 60 words cover a genuinely complex dual-mode tool.

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 tool with dual create/replace semantics, destructive replacement behavior, and a rich output schema, the description covers all that matters: the two modes, the data-loss risk, the safe update starting point, and the non-saving validation alternative. Return-value details are handled by the output schema, so nothing essential 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 coverage is 100% and the body parameter's own description already carries the replacement warning and the 'Record values go in rdata' hint, so the baseline is 3. The tool description adds the create-versus-replace trigger (id omitted vs. present), reinforcing and slightly extending what the schema states, which justifies a point above baseline.

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 names concrete verbs and resources — 'Creates a zone profile when id is omitted, or replaces the profile with that id in its entirety' — and immediately contrasts the two modes an agent needs to disambiguate. It also differentiates from the sibling family (get, check, delete profile) well enough that an agent can pick it out without opening the schema.

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?

Provides explicit routing: 'start from eurodns_dns_get_zone_profile when updating' and 'eurodns_dns_check_zone_profile validates a candidate first without saving.' This tells the agent exactly when to use this tool versus its alternatives and gives the safe workflow for update versus validate.

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