refresh

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

With no annotations supplied, the description carries the full disclosure burden and does explain the core effect: cached reads are discarded, so downstream reads re-derive from the live document. It does not state the return value or confirm the operation is cheap/side-effect-free on the score itself, though the "[READ-ONLY: not yet confirmed by the live harness]" note at least flags that safety metadata is unverified.

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 effect, then the trigger condition, in two compact clauses with no padding. The bracketed harness-verification note is meta rather than task-relevant, but it is short and clearly delineated.

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 zero-parameter, no-output cache-invalidation tool this is nearly complete: an agent knows what it does, what it invalidates, and when to call it. The only gap is whether subsequent reads are guaranteed fresh or whether some cache layers persist.

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 no parameter meaning for the description to add. Baseline 4 applies; the description correctly avoids inventing scope arguments.

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 concrete verb and object — "Forget cached reads" — and enumerates exactly which cached data is affected (time signatures, dynamics, keys, structure), which is far more informative than the bare name "refresh". It does not name a sibling to contrast against, so differentiation is left implicit rather than asserted.

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?

"use after editing in Dorico by hand" gives a clear, actionable trigger condition. It stops short of saying when NOT to call it, e.g. that it is unnecessary after the agent's own tool-driven edits because those presumably invalidate the cache themselves.

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