dubbing_render

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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds real value on top: it explains the mechanism behind idempotency (finished lines reused, pending ones resumed), discloses the conditional output (preview MP4 only when the video was downloaded), and states the speedup constraint. It stops short of disclosing cost, runtime, or what happens if speakers are unassigned, which is the remaining gap for a long-running render.

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 primary action and its outputs are front-loaded, and the optional background clause and rerun clause follow in a sensible order. It is a dense single paragraph with no filler sentences, though the parenthetical about speedup sits awkwardly mid-sentence and slightly interrupts the output enumeration.

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?

An output schema exists, so return values need no explanation, and the description covers outputs, resumability, optional background mixing, and the speedup constraint. What is missing for a mutation tool in a multi-step pipeline is the precondition set — that voices must be assigned and translation set beforehand — and any note on runtime or failure modes, which keeps it from a 5.

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 0% across 8 parameters, so the description must carry the load. It gives real meaning to three of them — max_speedup (1.0-1.5 range, applied only when needed), background_file (music/effects mixed under the voices), and preview_video (conditional on video being downloaded) — but says nothing about model, audio_format, background_volume, language, or project_id, leaving half the surface documented only by a bare type and default.

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 chain ('voice every translated line... then build the dubbed audio track') and enumerates the concrete artifacts produced: dubbed audio, translated SRT, and a preview MP4. It is clear what the tool does, though it never explicitly contrasts itself with siblings like dubbing_set_voice or dubbing_export_youtube_package, so differentiation is inferred from the pipeline stage rather than stated.

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?

Usage is implied rather than stated: 'every translated line' and 'its speaker's voice' hint that translation and speaker assignment must already exist, but the description never says 'call after dubbing_set_translation and dubbing_assign_speakers' or names any alternative. The only explicit guidance is the re-run behavior ('Re-running reuses finished lines and resumes pending ones'), which is helpful but is a rerun rule, not a when-to-use rule.

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