narrate

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

With no annotations present, the description carries the full burden. It discloses that the tool blocks until finished, returns the spoken duration, and uses macOS say. It also reveals the important limitation that live audio isn't captured in recordings, which is critical 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?

Two sentences plus a note, all informative with no filler. It front-loads the action and includes the key caveat in a clearly marked note.

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 simple speech tool with three parameters, the description fully covers purpose, behavior, blocking semantics, return value, and workflow integration. The lack of output schema is mitigated by explicitly stating the return value (spoken duration). Complete for its complexity.

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?

The input schema already provides 100% coverage with descriptive text for text, rate, and voice. The description does not add additional parameter-level meaning beyond noting the macOS 'say' implementation, so it doesn't exceed the baseline of 3.

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 clearly states the tool speaks narration live through speakers using macOS 'say', with a specific verb ('speak') and resource ('narration'). It distinguishes itself from render_narration and mux_narration by emphasizing 'live' and noting that audio isn't captured for recording.

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?

Explicitly notes that live audio is not captured in the recording and directs users to render_narration + mux_narration for the final cut, providing clear exclusions and alternatives. Also explains it's useful for pacing, giving context for when to use.

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