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

The clause 'the saved score is unchanged' adds real behavioral context consistent with the annotations (readOnlyHint=false, destructiveHint=false) — it tells the agent the mutation is confined to the pending preview. But it doesn't say whether the discarded preview can be regenerated, or what the discarded state leaves behind.

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?

A single compact sentence with the action front-loaded and the important consequence attached via the semicolon. Nothing is wasted, though the brevity leaves the gaps noted elsewhere.

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 two-required-parameter mutation with no annotations detail and no output schema, the description should at minimum indicate how to obtain the preview_id and what the caller sees afterwards. It covers the effect on the score but not enough to invoke confidently.

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?

Both required parameters (score_id, preview_id) have 0% schema description coverage, and the description never references them. An agent gets no hint about where preview_id comes from or how it relates to score_id.

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 (discard) and resource (a pending suggestion), plus the key invariant that the saved score is unchanged. It implicitly stands apart from the sibling apply_score_preview, though it never names that counterpart, so an agent has to infer the pair.

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?

Usage is only implied: there must be a pending suggestion generated by a preview. It never says when to choose this over apply_score_preview or what state is required before calling, leaving the discard-vs-apply decision to inference.

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