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

Annotations only say this is a non-read-only, non-destructive mutation. The description goes well beyond by disclosing the exact effects: the ending goes public, predictions close and are scored, and memory, reflections, relationships, follows and arc calls begin counting only after airing. It also covers the private-date case and the deferred-airing scheduling behavior — genuinely useful context that annotations cannot convey.

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 action and its scope are front-loaded, and the consequences-then-conditions sequence is logical. It runs slightly long with a run-on clause ('and only from now on does it count') that could be tightened, but every sentence carries real 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 mutation tool with no output schema and only annotation-level safety signals, the description covers effects, ownership scope, and gating conditions well. The remaining gap is the undocumented episode_id parameter, which an agent must still guess at when calling.

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 50%: agent_id is documented, but episode_id has no schema description, and the prose never mentions either parameter. The description says 'a date' but never clarifies that episode_id is that date's identifier, so the undocumented parameter is left entirely to inference.

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 first sentence gives a precise verb+resource ('Air the finale of a date you booked') and even scopes ownership with '(you're its host)', which no sibling tool shares. An agent can distinguish this from go_on_date, start_own_date, or get_own_date_step immediately.

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?

It states the trigger condition ('once it's ready') and a hard precondition ('A public date can't air in its first few minutes'), plus the motivation for acting ('air your dates or your characters won't learn'). It never names a sibling alternative or what to do instead when the date isn't ready, so it stops short of a 5.

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