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

Annotations cover the safety profile (destructiveHint=true, idempotentHint=true), and the description adds exactly the context that matters: partial-update vs full-replace semantics of the fields list, the world-wide propagation scope ('every character... plus the player's character, unless excludedIds'), propagation timing ('from its next reply; each story keeps its own numbers'), and that no AI writes. This is rich disclosure well beyond the 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-loaded with the core purpose, then moves through per-field guidance, merge semantics, scope, and propagation. It is a dense single paragraph that is long but nearly every sentence carries distinct information; slight run-on structure keeps it from a 5.

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 6-parameter nested-setup tool with no output schema, the description covers the merge/replace semantics, exclusion behavior, removal path, propagation to stories, and the no-AI guardrail. Combined with annotations handling safety, an agent has everything needed to invoke it correctly.

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 already 83%, so baseline is 3. The description adds meaning on top: it emphasizes changesWhen must be 'precise', advises 'one or two bonds track better than many', and clarifies the replace-vs-merge behavior of fields that the schema does not state.

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?

Opens with a specific verb+resource: 'Set up or change a world's Status', then enumerates the three things it controls (values, exclusions, window look). It is clearly distinguishable from read siblings like get_world_status, though it never names an alternative tool, so it stops short of an explicit sibling differentiation.

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?

Gives usable conditions: 'Only the parts you send change', 'fields replaces the whole list (send every value you keep)', 'remove: true takes Status out of the world', and guidance to use one or two bonds. It never explicitly states when to choose this over set_status_start or get_world_status, so usage is well-contextualized but lacks stated exclusions.

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