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

Beyond the annotations (readOnly=false, destructive=false, non-idempotent), it discloses two key traits: nothing is persisted until the user applies the suggestion, and stale base revisions are rejected. It doesn't say what a rejection returns or what the tool's response contains, but it adds genuine behavioral context the structured fields cannot express.

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, with the effect ('pending suggestion ... without changing the saved score') front-loaded and the revision constraint as a short trailing clause. Every clause carries 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 three-parameter, nested-object mutation-with-no-output-schema tool, the description covers the workflow but not the return value — an agent doesn't know whether it gets a preview handle/id or how the promised Apply/Discard is then triggered. Adequate to call correctly, incomplete for the full round trip.

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?

With 67% schema coverage, the schema documents revision and operation but only mentions the revision 'from the latest read or edit'; the description adds the consequence — a stale revision is rejected — which explains why the parameter exists. The bare score_id and the nested operation object get no extra detail, so it isn't a full compensation for the coverage gap.

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?

It states a specific verb and resource ('Show a proposed operation as a pending suggestion') and pins the scope with 'without changing the saved score', which separates it from edit_score/save_score_edits. It also points at the downstream Apply/Discard flow, so an agent can place it in the preview family without opening sibling schemas.

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 description makes the use case clear: propose an operation that the user must Apply or Discard in the panel, so the saved score is untouched. It stops short of naming apply_score_preview/discard_score_preview or explicitly stating when to prefer edit_score instead, leaving the agent to infer the routing.

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