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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is known. The description adds the state consequence ("leaves the deck"), which is real value, but it does not say whether the cue is permanently destroyed or merely removed from the deck while its data persists, nor whether the action is undoable — the most important remaining question for a destructive tool.

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 short sentence, front-loaded with the action and followed by the effect. The "like skip in the app" clause is the weakest part — evocative but imprecise — though it costs almost no length.

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?

This is a destructive, non-read-only mutation with no output schema, so the description must carry the behavioral load and largely does not. An agent cannot tell from this text whether the cue is permanently deleted or only removed from the deck, whether the operation can be undone, or what a caller learns afterwards. The app analogy does not substitute for those facts.

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?

There is a single parameter with 100% schema description coverage; the schema already explains it is "The cue id from list_cues" and even links it to the discovery tool. The description contributes nothing further about the identifier, so the baseline 3 applies rather than a higher score.

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?

"Skips a cue" names a specific verb and resource, and "so it leaves the deck" clarifies the effect on state rather than just restating the title. It is clearly distinct from read-only siblings like get_cue and list_cues, though it never explicitly contrasts 'skip' with a delete/archive concept, which is the ambiguity an agent would want resolved.

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?

"like skip in the app" gives an analogical usage cue, implying this is the in-product 'move past this' action rather than an editorial operation. There is no explicit when-to-use/when-not statement, no prerequisites, and no reference to a sibling alternative (none of the listed siblings do writes to cues, so there is little to route to). Usage is implied, not stated.

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