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

With annotations only covering the safety profile (not read-only, not destructive, not idempotent), the description carries the load and delivers: it states that 'pause' is a real cut that shifts everything after it, that 'continue' keeps speech/music/timeline intact while covering only the picture, that text/subtitle are burned and bound to the frozen frame, and that project scope is never guessed from the active pointer. These are non-obvious, consequential behaviors that go well beyond the annotations.

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-loads the project-scope guarantee and the core action well, and most sentences carry real information. However it is a single dense ~200-word paragraph with editorializing flourishes ('the pearl / power-phrase move') and repeated restatement of the audio_mode semantics, making it harder to scan than it needs to be.

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 13-parameter mutation with no output schema, the description covers the effect, all three audio modes, numeric ranges, and the binding behavior of text. The notable gap is the entire typography sub-system (font, template, color, accent_color) and any indication of how the inserted freeze frame is identified or removed later.

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 only 8% across 13 parameters, so the description must compensate, and it largely does: it defines at_output_s as the moment in the edited video, gives duration_s ranges and defaults (2-4s, default 1.0, 0.8-1.5 for a laugh), constrains blur to 0-1 and darken to 0-0.85 with classic values, enumerates motion behaviors, and explains all three audio_mode values. It leaves font, template, color, and accent_color entirely undescribed, which prevents a 5.

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 effect ('FREEZE the picture and hold it') and immediately scopes it as project-bound. An agent knows this creates a held-frame moment with optional burned text. It does not explicitly distinguish itself from close siblings like add_time_effect, add_zoom, or add_title_card, which keeps it from a 5.

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?

Gives real conditional guidance inside the parameter prose: audio_mode='continue' is for holding over an ongoing phrase without desyncing audio, audio_mode='hold' is the end-of-programme payoff, and it explicitly says to use 'hold' only when the source has no natural tail and to run restore_range first. The strongest exclusion/alternative pairing exists, though it is buried rather than framed as tool selection.

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