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

Adds materially beyond annotations: it charges two shared workshop quota units, performs no game mutation/persistence/publication/LLM calls, returns both branches plus trace witnesses of first divergence, and deliberately never declares an overall winner. Annotations only cover the generic read/write/idempotency profile, so the quota cost and non-mutation guarantees are genuinely new information.

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 action, then constraints, then exclusions. Dense but nearly every clause carries operational meaning; the trailing negatives list is the least efficient part.

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 5-parameter, 0%-coverage tool with an output schema, the description covers behavior, side effects, and scope exclusions well, and it points at the returned export rather than re-describing it. Remaining gap is per-parameter detail and how required vs optional inputs interact.

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 0%, so the description must carry parameter meaning; it clarifies that source_a/source_b are GardenScript farm.v1 policies, journal_json is a complete v4 journal, and budget/days are the 0–1000 ceiling and 1–7 day window. However it omits the 16384/65536 length limits, defaults, and how the call budget maps to the single budget_credits field.

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?

States a specific verb and resource — comparing two GardenScript farm.v1 policies from the same v4 journal — and pins the scope tightly (two trials, 1–7 days, identical 0–1000 ceilings). An agent can distinguish it from farm_policy_run and farm_compare_get without opening schemas.

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 clear preconditions: both policies must come from the SAME complete v4 journal and a finite call budget must be agreed first, with two trials of matching duration and credit ceilings. It also rules out adjacent features (no legacy future-veto helper, no v5 weather, no official ranking), though it never names the sibling tools it substitutes for.

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