Change a world setting

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

Annotations already indicate readOnlyHint=false, destructiveHint=true, and idempotentHint=true. The description adds that the value is checked against choices and range and read back, which gives insight into validation and confirmation behavior. However, it doesn't explicitly state that changes are destructive or permanent, but the annotations cover that. It also mentions the write switch, which adds context about permissions beyond the schema.

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?

The description is concise at three sentences and front-loads the most critical constraint (the list of allowed settings) and the permission requirement. It includes only essential information without redundancy, such as the validation behavior. Every sentence carries weight.

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?

Given the tool's moderate complexity (4 params, no output schema) and rich annotations, the description covers the key context: the allowed settings list, the value types, the validation, and the write switch. The schema covers parameter details. The description doesn't mention the return format, but the 'read back' phrase suggests confirmation. An agent can correctly invoke this tool based on the description plus schema, with the only minor gap being the exact response structure.

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 all parameters are described in the schema. The description adds that values can be text, number, or true/false, which maps to the 'value' parameter's generic description but adds type enumeration. It also mentions the write switch, which is not a parameter but relates to dryRun (since dryRun needs no write permission). However, the description doesn't elaborate further on each parameter, so 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 clearly states the verb 'Change' and the resource 'world setting', and importantly restricts it to a specific list of settings the AI may change, distinguishing it from generic setting tools. It also mentions the value types and validation, making the purpose specific and non-tautological. This differentiates it from siblings like list-settings and get-world-info.

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 explicitly says when to use this tool: only for settings on the list that list-settings names, and it notes that the list is empty until the Gamemaster decides. It also mentions the need for the write switch, implying permission requirements. It also implies when not to use it (settings not on the list) and points to list-settings as the alternative for seeing available settings.

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