randomize_rack_macros

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

Annotations already cover safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=true). The description adds genuinely non-redundant behavior: randomization is native and non-deterministic with no seed, it binds exact rack and parameter state, and it reports observed values rather than a guaranteed result. It could still note that existing macro values are overwritten by the invocation.

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?

Three short sentences, front-loaded with the action, then the state-binding behavior, then the non-determinism caveat. No filler and every sentence carries distinct information.

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 non-deterministic mutation tool with a dry-run/confirmation-token workflow and no output schema, the description covers purpose, precondition, and the nature of the result. It is close to complete; only the side effect on pre-existing macro values is unstated.

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 description coverage is 100%, so parameter documentation is already complete (dryRun, planHash, confirmationToken, expectedStateVersion all explained). The description adds only the conceptual plan-vs-invoke split, which the schema's dryRun description already carries, so baseline 3 applies.

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 pair (plan/invoke) and resource (Live's native randomization of eligible mapped rack macros), plus the scope constraint 'eligible mapped'. An agent can distinguish this from sibling variation tools such as store_rack_macro_variation or recall_rack_macro_variation without opening a schema.

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?

'Plan or invoke' plus the dryRun semantics make the two intended modes clear, and 'no seed or predictable outcome is available' warns the agent that retries won't reproduce results. It stops short of 5 because it never names an alternative tool or an explicit when-not-to-use condition.

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