list_local_splice_roots

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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: this inspects the local environment (detected macOS defaults) and performs no network/verification side effects, which matters given openWorldHint=true. It does not describe ordering or pagination of the returned roots.

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 tight sentences: what it lists first, what it does not do second. No filler, no restatement of the tool 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?

With no output schema, the description carries the return-shape burden and does so adequately by naming the two kinds of roots returned (detected defaults and configured paths). Missing are any hints about result count, ordering, or what to do when no roots are found, but for a zero-param list tool this is close to sufficient.

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, which is the baseline-4 case; there is nothing to disambiguate. Schema coverage is also 100%, so no compensating detail is required.

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 (list local Splice roots: folders and cache paths) and immediately scopes what is included (macOS defaults plus explicitly configured roots). An agent can tell this apart from browse_local_splice_directory and search_local_splice_samples 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?

The second sentence gives explicit exclusions — no cloud asset search, no license verification, no downloads — which clearly bounds the tool's territory. It stops short of naming the sibling tools (browse_local_splice_directory, search_local_splice_samples) that handle the excluded work, so routing is inferred rather than stated.

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