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

Annotations already declare readOnlyHint=false and destructiveHint=true, but the description goes well beyond them: it discloses that a managed provider may be contacted, that BYOK validation occurs, that preview-rate and voice-availability state can be written, that credentials have no platform fallback, and that audio is bounded in-memory WAV. That is exactly the extra context needed for a non-idempotent, destructive, open-world 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?

Three tight sentences with zero filler, and the most decision-relevant facts (bounded/rate-limited preview, state writes, not read-only or free) are front-loaded before the size limits. Slightly dense but every clause carries weight.

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 an 11-parameter, nested-object tool with no output schema, the description covers side effects, credential behavior, and the return shape (bounded in-memory WAV) well. Remaining gaps are modest: rate-limit magnitudes, failure/fallback behavior, and the interaction between the required provider/model combo and the optional credential_id.

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 55%, so the schema already documents several optional params (credential_id, organization_id, delivery, agent_id, audio_environment). The description restates the 200-character text bound and adds the return format, but says nothing new about the five required params or how delivery/language interact, so it neither compensates for the coverage gap nor adds much beyond the schema.

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 first sentence names a specific verb and resource ('Render ... TTS preview'), qualifies it with real scope modifiers (bounded, rate-limited, provider-backed, authenticated workspace), and no sibling tool overlaps it. An agent can distinguish this from get_agent_voice_stack or preview_simulation_run without opening a 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?

It conveys real usage context ('validate BYOK', 'exact pinned managed voice retry' via agent_id) and warns that this is not a free/read-only probe, which implicitly tells the agent when not to call it casually. But it never names an alternative tool or states the precondition under which this preview should be preferred over set_agent_voice_stack or test_phone_server, leaving routing to inference.

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