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

Annotations only cover the safety profile (not read-only, non-destructive, non-idempotent); the description adds genuinely new behavior: async execution returning toolExecutionId, the need to poll, and the synchronous short-circuit for local calls. It also introduces the 'supportsDirectToolExecution' voice constraint, which is meaningful context. Missing error/timeout behavior keeps it from a 5.

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 compact sentences, front-loaded with what the tool produces, followed by the async contract. Minor redundancy in restating return fields covered by the output schema, but no filler.

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 listing fileId/downloadUrl/file metadata is somewhat redundant, but the description correctly covers the async polling lifecycle and the local synchronous path. No required parameter is left unexplained.

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 description coverage is 100%, so the schema already documents text, speed, voiceId, and language with format and bounds. The description only adds a quality constraint on voiceId (must support DirectToolExecution). Baseline 3 is appropriate since the schema does the heavy lifting.

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 (synthesize) and resource (spoken audio from text) and ties it to a catalog voice, which cleanly separates it from generate_music and generate_sound_effect siblings. It does not explicitly address the closest alternate, voiceover_to_video, so it falls just short of full sibling differentiation.

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?

The description gives a real usage instruction – poll get_tool_execution for status/results on hosted clients – and names list_tts_voices as the source of voiceId. However, it never states when to prefer this over the adjacent audio-generation siblings, so usage is implied rather than fully guided.

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