Plan Filler Word Removal

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

Annotations already carry readOnlyHint=true, idempotentHint=true, and destructiveHint=false; the description strengthens this with a host-specific, actionable claim ('Local-only; never changes Premiere') rather than merely repeating annotation text. It also discloses the result behavior (frame-snapped removal and keep ranges plus apply routes) that an agent would want before calling. No contradiction with any annotation.

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?

Three sentences with zero waste: purpose (with examples), output artifacts, and safety guarantee. The most important information is front-loaded in sentence one, and each subsequent sentence earns its place by answering a distinct question an agent would have (what do I get back? does this mutate anything?).

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 moderately complex tool — 7 params, a nested word_timeline object, and an output schema — the description plus the 100%-covered schema covers the essentials: purpose, input binding constraint, output shape, and non-destructive behavior. The only notable gap is not naming the downstream apply route (e.g., apply_edit_plan) explicitly, though the 'apply routes' phrase hints at it and the output schema presumably documents the plan structure.

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% — every one of the 7 parameters has a detailed schema description covering defaults, matching semantics for filler_words, frame-snapping for frame_rate, handle_frames behavior, and revision binding for word_timeline. Per the rubric baseline, when coverage exceeds 80% the description need not duplicate parameter details, and it doesn't add significant param semantics beyond 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?

Opens with a specific verb+resource ('Plan word-level filler removal') and immediately scopes it with concrete examples ('um, uh, you know...') and an input constraint ('revision-bound word timeline'). The second sentence names the exact output artifacts ('frame-snapped removal and keep ranges plus apply routes'), which distinguishes it from near-siblings like plan_word_mute_ranges (mute vs. remove), plan_pause_tightening, and plan_silence_review_markers. This is far from a tautology — it adds real specificity beyond the name.

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 conveys clear context for when this tool is appropriate: it is a planning-stage operation that runs locally and never touches the Premiere project, so an agent knows it can be invoked safely before any editing step and that its output (apply routes) feeds a downstream apply phase. However, it never explicitly names alternatives or exclusions — e.g., it doesn't say 'use apply_edit_plan to execute the plan' or contrast itself with plan_word_mute_ranges — leaving some routing to inference.

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