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

The annotations only provide the generic safety profile (not read-only, not destructive, not idempotent, open world). The description goes well beyond them, disclosing that the generated audio is written into the step, that step duration is extended, that the monthly Pro audio quota is consumed, and that video steps return 400. It does not cover authentication requirements or concurrency behavior, which is the only notable gap.

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 a single dense paragraph. It places the most important information first (what is generated and where the output goes), then the quota, then failure modes; almost every clause carries new information for an agent.

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 a mutating tool with no output schema, the description covers the important consequences: audio persistence, step duration change, quota consumption, caching, and the 400 error path. The only gap is a precise description of the success response, which matters less because the tool has no output schema.

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 83%, so the baseline would be 3. The description adds value beyond the schema by explaining the text resolution precedence among the text, narrationScript, and title+text sources, which the schema does not spell out; the lang parameter's caching behavior is covered inside 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 description states a specific verb and resource (generates spoken narration for a step), the output format (MP3 mono 64 kbps, 24 kHz), and the side effect (audio is attached to the step and the step's duration grows to fit it). That makes it clearly distinguishable from the sibling generate_step_text, which produces text rather than TTS audio.

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?

Usage context is clear: it draws on the monthly Pro audio quota of 30 min/month, and steps containing YouTube/Vimeo video cannot be narrated and return 400 with a stated reason. It does not explicitly name which sibling to use instead (for example generate_step_text or translate_tour), so it stops short of full explicit routing.

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