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

Annotations only declare readOnlyHint and openWorldHint; the description adds real behavior the agent could not infer — an interactive picker appears in widget-capable clients and the chosen voice_id returns as the next user message, whereas text-only clients must relay the list with preview links. It also discloses the provider/model compatibility constraint, which prevents a wrong downstream call.

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?

Dense but well front-loaded: purpose and provider semantics come first, widget/text-client behavior and the voice_id handoff follow. Every sentence carries information, though the passage runs long for a list tool and could be tightened.

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?

There is no output schema, but the description covers the return shape relevant to the agent (list carries preview links) and the widget handoff path for voice_id. Combined with annotations covering the safety profile, nothing needed to invoke or route this tool is missing.

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 100%, so the baseline is 3, but the description goes further by explaining provider semantics (a voice only works on its own provider's models), the seed-tts vs seed-audio distinction, and that gender/language/limit are optional filters. It adds genuine meaning beyond the schema, though it does not extend the schema's filter syntax examples.

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 (list TTS voices for popcraft_generate_audio), and immediately scopes it with the kind:"tts" constraint and provider split, which no sibling tool covers. An agent can distinguish this from popcraft_models_explore or popcraft_generate_audio without opening any schema.

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?

Explicitly names the consumer tool (pass voice_id to popcraft_generate_audio), gives an exclusion (model:"seed-audio" needs no voice), and adds a temporal rule ('call once per voice-selection conversation — do not re-list unless the user asks for different filters'). This is when/when-not guidance in the strongest form.

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