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

Annotations already declare readOnly/idempotent/non-destructive, so the lower bar applies, yet the description still adds required permissions (agents:read or coverage:read) and describes the returned data shape (cost, latency, languages, streaming, runnability, conversation_engines). The only gap is pagination/size behavior in a presumably large catalog.

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?

The lead sentence front-loads the purpose and filters, but the middle clause about has_language_axis, per-language overrides, and 'Follow the caller' is dense and hard to parse. Structure is otherwise linear and mostly waste-free.

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?

With no output schema, the description compensates by enumerating return fields, conversation_engines values, and auth requirements for a moderately complex catalog tool. The awkward has_language_axis passage leaves some ambiguity about the per-language override rows, but nothing critical to invoking the 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 0%, so the description carries the burden, and it delivers: it names component, language with two worked examples showing filter semantics, and metered_only. It does not fully explain what metered_only excludes or the accepted form of component beyond the enum, but the semantics are largely covered.

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 ('List') and resource ('selectable STT/LLM/TTS voice-stack providers') and enumerates the returned attributes (cost, latency, languages, streaming, runnability) plus conversation_engines. This distinguishes it clearly from siblings such as get_agent_voice_stack (a specific agent's stack) and get_capabilities.

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?

It states an auth prerequisite and gives concrete filter usage examples (language=et, language=si), which implies the discovery use case. However, it never explicitly says when to reach for this catalog versus get_agent_voice_stack or list_audio_environments, so alternative selection is left to inference.

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