pob_update_skill_group

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds genuinely non-obvious domain behavior (the first gems element for an item-granted skill carries the skillId in id with sourceIndex 1, followed by supports), but it never says whether the supplied gems array replaces the existing group wholesale or what happens to gems omitted from it — the most important destructive consequence.

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?

Four short sentences, front-loaded with the action, so there is little waste. However the final sentence ('the fields of the first element and the name of such a skill are set by the source') is vague to the point of being unusable, and the item-skill special case is buried rather than structured as a conditional.

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?

This is a destructive mutation with 0% schema coverage and no output schema, so the description carries full burden — yet it omits replace-vs-merge semantics, what a successful response looks like, and the meaning of most fields. It documents one edge case well but leaves an agent unable to call it confidently for the common case.

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 parameter meaning, yet it only clarifies sourceIndex and the id field in the item-skill case. groupId, label, level, quality, and enabled are left entirely unexplained, and the constraint that sourceIndex comes 'from the report' is stated without saying what that report is or how to obtain it.

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 opening clause 'Изменить группу' names a specific verb (modify) and resource (skill group), and the reference to the source SkillsTab scopes where the change lands, which distinguishes it from pob_add_skill_group and pob_delete_skill_group by name. It stops short of 5 because it never states plainly what 'modify' means operationally (replacing the gem list vs. patching it).

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 description gives one concrete usage rule — pass sourceIndex taken from the report for saved gems — and one conditional case for item-granted skills. It offers no explicit when-to-use/when-not-to-use guidance relative to add/delete skill group or select_main_skill, leaving the routing to be inferred from the tool name.

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