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

The description discloses consequences beyond the annotations: an empty list removes cues, speech is preserved, global mute still applies, unsupported changes are refused without rebuilding, and retries must preserve operation_id and exact inputs. These details materially supplement the destructiveHint and idempotentHint annotations without contradicting them.

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 purpose is front-loaded and most sentences carry operational value. The description is long and telegraphic across several sentences, so it loses some crispness but avoids obvious filler.

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?

Given a mutation with a nested cues array, an output schema, and annotations covering destructiveness and idempotency, the description supplies the missing prerequisites, refusal behavior, retry guidance, and cost context. An agent has enough information to invoke it correctly.

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 83%, so the structured schema already carries most parameter meaning. The description adds useful semantics for cue names from scenes.soundOptions, word indices from soundWords, and retry handling for operation_id, though it does not explain cue fields such as on, gain, or offset.

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 first sentence names a specific verb and resource: replacing this scene's added sound cues. The scope is clear enough to distinguish it from video-level sound tools such as set_video_sound_effects, and the empty-list behavior is stated immediately.

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?

It gives clear prerequisites: read get_project_context first and pass base_version and selected output_id. It also directs file requests to check_video with_download and says to preserve operation_id on retries. It does not explicitly contrast this tool with sibling sound-editing tools, keeping it below 5.

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