render_narration

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

With no annotations, the description carries full burden. It discloses several processing behaviors: per-sentence generation, jittered pauses, soft in-breaths, and -16 LUFS normalization, plus the engine fallback. This is substantial context, though it does not mention side effects like file overwrite/path creation or error behavior, which would push it to 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?

The description is two compact sentences, with the primary purpose and return value front-loaded in the first sentence. The second sentence packs key behavioral details without fluff. Every word contributes value, and no information is redundant with the schema.

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 tool with 6 parameters, no annotations, and no output schema, the description covers the main contract: what it does, engine fallback, processing traits, and the return value (exact duration). It lacks details on default output format and the exact return type, but given the complexity, the description is largely complete, meriting a 4.

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 baseline is 3. The description adds meaningful context beyond the schema, particularly for the 'engine' parameter (explains when Voicebox vs say is used) and for the 'text' parameter (relates per-sentence generation and pauses to how text is processed). This extra semantic richness justifies a 4.

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 uses a specific verb ('render') plus resource ('a narration line to an audio file') and states the key outcome (return EXACT duration for muxing/pacing). It clearly distinguishes this tool from siblings like narrate (which implies playback), voicebox_status (status check), and mux_narration (muxing), by focusing on audio file generation with duration.

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 context on when to use the tool (for muxing/pacing) and explains the engine 'auto' behavior with a fallback to macOS say, which guides selection among engine choices. It does not explicitly name alternative tools for exclusion, but the purpose statement and sibling list make it clear that this is the rendering step, distinct from status checking or muxing.

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