Цели стратегии

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

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true. The description adds valuable non-obvious context: that changing goals restarts strategy training (a destructive side effect) and that the server reads the current list itself (an extra API call). It doesn't detail auth requirements or rate limits, but adds meaningful behavioral context beyond 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-loads the core purpose, then mode explanation, then warnings. Every sentence carries information, though slightly dense. Uses a warning symbol to draw attention to the training restart.

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 3-parameter mutation tool with no output schema and rich annotations, the description covers purpose, modes, supported campaigns, goal ID source, destructive side effect, and the server reading current list. It doesn't explain what happens to goals not mentioned in add vs remove modes beyond the mode descriptions, but is largely complete.

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 baseline is 3. The description reinforces mode semantics and states value is in roubles and required for goals, plus mentions GoalId 13 for maximum conversions. The schema handles specific parameter details; description adds the 'why' and edge cases like empty array clearing.

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 (set strategy PriorityGoals) with their rouble value, and explains the optimization purpose including the auto-strategy context. Distinguishes itself from sibling set_strategy by focusing specifically on campaign goals, not general strategy settings.

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?

Explicitly explains when to use each mode: add to add/change value of existing goals, remove to remove named goals, replace to replace the entire list. Includes a critical warning that replace with one goal erases the rest, guiding correct usage. Names which campaigns are supported.

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