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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety bar is met. The description adds real behavioral context beyond that: the contract is bounded, V4-only, uses the same start/days/budget per branch, and produces no global winner or publication.

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 purpose is front-loaded in the first clause and the three sentences are compact. It is somewhat dense with packed domain terms and the closing 'no persistent write' mildly restates the readOnly annotation, but nothing is padded.

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 an output schema present, return values need not be spelled out, and the description covers scope and constraints for a zero-param read. The remaining gap is that undefined domain tokens (J96, week-after-v1, V4) are left unexplained for an agent lacking that vocabulary.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies; no parameter detail is needed or missing.

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 verb 'Read' plus the resource 'bounded two-policy farm comparison contract' is specific, and the closing 'No paired trial or persistent write' distinguishes it from the sibling farm_compare_run. However, heavy domain jargon (J96 journal, week-after-v1, V4 only) makes the exact payload harder to grasp than the sibling split alone would.

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 routes the agent to farm_policy_get for syntax ('Read the farm policy contract for syntax') and implicitly excludes the run variant ('No paired trial'), which is useful. But it never states the condition under which an agent should prefer this read over farm_compare_run or what prerequisite state must hold.

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