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

Annotations only declare it is not read-only, not destructive, not idempotent. The description adds meaningful behavior beyond that: it consumes one shared daily date ('once a date'), never weekly dates or tokens, performs the entire remainder of the date in a single call, and returns { step, cost }. That quota/cost disclosure is exactly the kind of context the annotations cannot carry. It stops short of saying what happens if the date is already finished or the caller is the other live agent.

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?

Almost every sentence carries real information, but the structure is poor: it opens with a throat-clearing parenthetical about dates and tokens before stating the actual action, and the run-on side enumeration is hard to parse on first read. It is dense rather than bloated, but the ordering and phrasing cost comprehension.

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?

With no output schema, the description correctly supplies the return shape ({ step, cost }) and explains quota consumption and per-side scope. Given five parameters and only one required, the remaining gaps (preview, compact, agent_id) are covered by the schema's own descriptions, so the definition is close to sufficient for correct invocation.

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 coverage is 80%, so the baseline is 3; the description earns above that by expanding the key enum much further than the schema does — spelling out that 'mine' plays every non-live-agent side including the recap, and that 'a'/'b' plays one side while you write the other. It omits 'both' (which the schema does document) and says nothing about compact, preview, or agent_id, leaving those to the schema.

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 second sentence does state a specific action — the show's model performs the rest of a date you're performing in one call and returns the finished date or your next turn — but it is buried behind a dense parenthetical about shared daily dates and tokens. It never names or contrasts with the obvious siblings (submit_own_date_step, hand_over_own_date, get_own_date_step), so an agent must infer where this sits in the own-date workflow.

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?

'Lines you write yourself are free' and 'never your weekly dates or tokens' imply the cost trade-off and when this is appropriate, and the side enum explains which turns get played. However there is no explicit when-not-to-use or named alternative, and the preview capability (only described in the schema) is the real 'check before spending' guidance and isn't surfaced here.

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