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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent mutation; the description goes further by disclosing the timing model (~0.15s expo ease, hold to next cut or sentence end, cut back out), the overshoot behavior, and that omitted count/strength are derived from program length and the motion brief with explicit values winning. It does not state how to undo the punches or whether repeated calls stack, which keeps it below 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?

Front-loaded with the PROJECT-SCOPED scoping rule, then purpose, then behavior, then usage constraints. Every sentence carries information, but it is one dense run-on block rather than being broken into scannable segments.

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 mutation tool with no output schema, the description covers scope, effect, defaults, and when to abstain. Remaining gaps are the return shape and valid ranges for count/strength, both minor given the annotations already signal a safe, non-destructive edit.

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 coverage is only 33% (count and strength are bare integers/number with no descriptions), so the description must compensate. It does add real meaning: the two omitted values are auto-derived from program length and motion brief, are distributed rather than clustered on adjacent loud words, and explicit values override — though units and valid ranges for count/strength are still absent.

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 and resource — punch-ins on the vocally stressed words of speech — and frames itself as 'the short-form talking-head emphasis pass,' which separates it from a manual add_zoom or a suggest_emphasis-style suggester. The parenthetical on how stress is measured (from audio, with real word timestamps and face targets) makes the operation unambiguous.

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 marks the pass as OPTIONAL and never required, then gives concrete skip conditions: calm/minimal briefs, footage without speech, or when the type already carries the moment. It also warns against over-application (a punch on every stressed word looks childish) and tells the agent to keep a small count.

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