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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the risk profile is known. The description adds genuinely new behavioral facts beyond that: the change is a single reversible undo step retrievable via undo_storyboard, and the call consumes no credits — both material for an agent weighing a destructive mutation. It stops short of saying whether omitted fields are left untouched or reset.

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?

Three tight sentences, front-loaded with the verb and resource, then addressing, then behavior. No filler. The first sentence is dense but readable, and the trailing cost note is short enough to earn its place.

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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. The description supplies the addressing model, null handling, reversibility and cost — enough to invoke correctly. The remaining gap is the unstated meaning of several nested `changes` fields and whether unspecified fields are preserved.

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?

Schema description coverage is 0%, so the description must carry the load, and it partially does: it explains that `sound` accepts an array index or a uuid (matching the anyOf), and that null `from_scene` opens that end of the span. But nested fields such as source_in_seconds / source_out_seconds, start_offset_seconds, loop_duration_seconds, the length enum values (loop/once/in_full) and the gain_db bounds are only gestured at ("source window, length or gain") with no semantics.

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?

"Change one sound card" gives a specific verb and resource, and the clause "addressed by its number in the answer's sounds array or by id" plus the list of editable facets (start, source window, length, gain) makes the scope concrete. It is distinguishable from add_storyboard_sound and remove_storyboard_sound by the mutation verb, though it never names those siblings explicitly.

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 implied rather than stated: the description gives the reversal path ("One undo step; undo_storyboard takes it back") and the cost condition ("Spends no credits"), which help an agent decide to call it. However, there is no explicit when-to-use vs add_storyboard_sound / remove_storyboard_sound / update_scene, and no statement that the target sound must already exist.

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