speech_generation

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses that the tool rejects direct calls without an active skill grant/run descriptor, and that if a result is queued/running the agent should return the task id and stop. It also hints at an approval process for voice profiles, adding useful behavioral context.

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 description is three concise sentences, front-loaded with the core action. Every sentence adds value: what it does, the required prerequisite, and a critical async/queued behavior warning. No fluff or repetition.

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?

Given the tool's complexity—12 parameters, no output schema, minimal annotations—the description covers the critical prerequisite and queued-task behavior, but omits the success return format and does not describe most parameter semantics. It is adequate for initial selection but not fully complete for safe invocation without further investigation.

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?

With 12 parameters and schema description coverage of only 17%, the description should compensate by explaining key parameters. It only vaguely references 'approved voice profile' and 'project reference assets', which map to a few parameters, but provides no meaningful guidance on format, sample_rate, pitch_rate, duration, or model_option_id. The schema enums/ranges are not enough, and the description adds little beyond them.

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 description opens with a specific verb and resource: 'Generate a speech audio asset', which clearly distinguishes it from sibling tools like music_generation and video_generation. It adds optional qualifiers ('voice profile or project reference assets') that refine the tool's scope without ambiguity.

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 provides clear usage context by stating 'Call run_skill first' and explicitly warns against resubmitting queued/running tasks. While it does not name alternative tools, the prerequisite and the 'do not submit again' instruction give practical guidance on when and how to use the tool.

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