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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds genuinely non-annotated context: no LLM call (deterministic) and no persistence ('stores nothing'), plus the untrusted-input framing. It does not, however, say what a failure looks like or whether compilation has side effects on disk.

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?

Two short sentences, front-loaded with the core action and followed by the two constraints that matter most. No filler or restatement of the name.

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?

An output schema exists, so return-value explanation is unnecessary, and the description covers the action, safety posture and determinism. It is slightly thin on the input semantics and on what the validation result communicates, but nothing critical for invocation is missing.

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% – the single 'source' parameter has no description in the schema. The description only calls it 'an untrusted GardenScript source', leaving format (inline text vs. path), size limits, and syntax expectations unstated, so it does not compensate for the coverage gap. One parameter keeps the baseline from being lower.

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?

Specific verb pair (validate/compile) plus a specific resource (GardenScript source) and an implementation detail (local Rust compiler). It does not explicitly name a sibling, and several validate-flavored tools exist (strategy_validate, farm_policy_validate, artifact_verify), but the 'GardenScript' resource qualifier makes it distinguishable.

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?

The 'no LLM call' clause implicitly signals this is the deterministic/local validation path, which is useful context for choosing it over LLM-backed siblings. However, there is no explicit when-to-use, when-not-to-use, or named alternative guidance.

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