Get a zone profile, or list them

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: the mode-switching behavior (get-by-id vs. list when id is omitted), the content scope of a full profile ('records, URL forwards and mail forwards'), and the destructive-replace semantics of the sibling save tool. 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?

Two sentences with zero filler: the primary return behavior is front-loaded, the domain concept (profile vs. zone template) is established in a clause, and the critical read-before-save warning earns its place. Every sentence carries load-bearing information.

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 six-parameter, dual-mode tool, the combination is nearly complete: output schema documents return values, annotations cover idempotency and safety, the schema documents pagination and sorting, and the description covers the conceptual model and the save relationship. The only residual gap is that it never explicitly tells an agent to use eurodns_dns_get_zone when live zone data — not a profile template — is needed; it only implies the distinction.

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 schema's own parameter descriptions are unusually rich (pagination semantics, character-limit truncation, sortField spelling). The description's 'by id, or lists ... when id is omitted' restates what the id parameter schema already says ('Omit it to list the account's zone profiles'), so the description adds essentially no net-new parameter meaning beyond the structured data. 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?

The description names a specific verb and resource ('Returns one zone profile in full') plus a second mode ('lists the account's profiles when id is omitted'), and defines what a profile is ('reusable templates applied to new zones'), which distinguishes it from the sibling eurodns_dns_get_zone that targets live zones. It also explicitly names eurodns_dns_save_zone_profile as the counterpart, so an agent can tell this tool apart from its 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?

Provides explicit sequencing guidance: 'read one before eurodns_dns_save_zone_profile', with the reason attached ('which replaces the whole profile with what you send'). This tells the agent when to call this tool in a workflow, but it does not state any explicit when-not or route to alternatives like eurodns_dns_get_zone for live zone data, so it stops short of full exclusion guidance.

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