Moonlight Garden Fishing Trip

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

Annotations only flag destructive/openWorld/non-idempotent, but the description adds far more: no separate purchase confirmation, fixed casting order, empty casts still consume bait/quota, failures halt remaining steps while retaining successes, timeout = UNKNOWN, and no automatic refunds/scheduling. This is rich behavioral context that goes well beyond the annotation flags.

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?

It is long, but front-loaded with 'ACTION TOOL' and organized around preconditions, execution order, failure semantics, and return semantics. Almost every sentence carries actionable detail; a few clauses (e.g., repeated purchase/cast-result wording) could tighten, but the density is justified given there is no output schema.

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 must explain returns, and it does: confirmed quantities/costs, EVERY purchase/cast raw result including empty casts and auto fish sales, purchaseTotalsComplete:false meaning (unknown purchases may have spent moon), and that remainingCastCountBefore is pre-execution. It is complete for this complex multi-step action.

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 100% (each int param already explains omitted=0 and auto-purchase), so baseline is 3. The description adds real value: the Chinese bait names (小面包虫, 月光虫, 星纹蚯蚓, 月华饵, 满月秘饵), the fixed execution order fullmoon→moonhalo→stardust→moonworm→bread, and 'one cast 1 <key> per rod,' which the schema alone does not convey.

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 opens with an explicit verb+resource: 'ACTION TOOL: automatically spends moon to buy missing bait from the shop, then fishes.' The multi-step action (buy-then-cast) and the five bait-keyed cast counts are unambiguous, and the tool is clearly distinct from the read-oriented siblings (daily_routine, farm_brief, recipe_check).

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 gives explicit preconditions and when-not rules: 'Check live daily quota, bait stock, shop prices and wallet first... buy NOTHING/cast NOTHING if quota or the entire bill is insufficient.' It also states there is 'No daily-once restriction; each invocation rechecks quota,' and instructs on the UNKNOWN-outcome case ('never automatic retry'), leaving little to inference.

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