flowforge_clone_voice

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

Annotations already declare destructiveHint=true, non-idempotent, open-world, and not read-only, so the safety profile is largely covered. The description adds a genuine post-condition (the new voice appears in catalog='cloned') and a licensing caveat, which are value beyond the annotations. It says nothing, however, about the delete half: whether deletion is irreversible, whether voices in use by assistants can be removed, or what gets destroyed.

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 short sentences, front-loaded with the verb and resource, no filler. Minor inefficiency: bundling create and delete in one opening sentence blurs the two operations instead of separating them.

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 needn't be described, and annotations carry the safety signal. Still, for a destructive tool the description leaves the delete semantics and its side effects on existing assistants unexplained, and it gives no prerequisites beyond the licensing caution. Adequate but not complete.

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?

Top-level coverage reads as 0% because the single 'params' field is a bare $ref, but the nested CloneVoiceInput schema documents every field thoroughly — action, confirm required for delete, provider options, 50 MB file limit, voice_id. The description therefore adds almost nothing parameter-level beyond restating that creation takes a local reference-audio file. Baseline 3, no extra credit.

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 and resource ('Create a cloned voice from a local reference-audio file') plus a second operation ('or delete one'), and names the sibling where results surface (flowforge_voice_catalog catalog='cloned'). The dual operation is collapsed into one sentence, so the delete half is only gestured at, but an agent can still tell this apart from flowforge_voice_catalog.

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?

Offers implied usage: clone when you need a custom voice, then find it in the cloned catalog. The only explicit directive is a compliance rule ('Only clone a voice the user has the right to use'), which is a policy constraint rather than when-to-use guidance. There is no statement of preconditions for the delete path or of alternatives for listing/removing voices.

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