Labels

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false; the description adds genuinely non-obvious behavior beyond that — that delete reconstructs only its own label track at the bottom of the project, preserves all other labels including overlaps, and that returned indices reflect the new order. That is meaningful disclosure of destruction scope and post-mutation state, but the description is silent on idempotency/repeat-call behavior and on what list/find actually return.

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 sentences, zero filler: the first front-loads the full action inventory and the second reserves detail for the one operation whose side effects need explaining. Every clause carries distinct information, and nothing is repeated from the schema or annotations.

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 five-action, eight-parameter tool with no output schema and no parameter descriptions, the definition covers the action space and the highest-risk path (delete) well enough to invoke safely. It is still incomplete on the four undocumented timing/track parameters and on the return shape of list/find, which an agent would have to probe. (Holistic view; the missing param semantics are already penalized above.)

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 coverage is 0%, so the description must carry the parameter burden, and it partly does: it explains that index is a flat, zero-based label index — real meaning beyond the schema's bare minimum:0 — and clarifies that find works on label text and regular creates markers rather than region labels. It leaves start, end, interval, and trackName entirely unexplained, which is a substantial remaining gap. (scored 4 per the low-coverage rule's demand on description; the unexplained timing and track-name parameters keep it from 5)

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?

The description enumerates the specific operations ("List/find labels by text, edit one flat zero-based label index, delete one label, or create regular markers") that map directly onto the action enum values, so an agent can tell what the tool does without opening the schema. It stops short of naming the sibling it is not — e.g., audacity_labels_set or audacity_labels_file — so differentiation from relatives is only implied by the phrase "flat zero-based label index".

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 conveyed implicitly by listing which action does what, and the delete sentence gives useful context about that specific action's safety. There is no explicit when-to-use/when-not-to-use guidance relative to audacity_labels_set or audacity_labels_file, and no statement of prerequisites (e.g., an open project or an active label track).

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