reels_set_audio

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

Annotations only declare it is a non-read-only, non-open-world, non-destructive write. The description adds genuinely new behavioral facts beyond that: the words array is a wholesale replacement rather than a merge, and passing null audio strips existing narration. What it omits is the concurrency contract behind the required 'revision' parameter and whether a stale revision is rejected.

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 short sentences, zero filler, with the core action front-loaded and the two non-obvious behaviors (replacement, null removal) following immediately. The terseness borders on under-specification rather than padding, which is the right failure mode here.

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?

With no output schema and only coarse annotations, the description should fully cover the contract of a mutation tool, and it leaves the required 'revision' semantics unexplained. An agent can form the right payload shape for audio/words but may not understand why revision is mandatory or what happens on mismatch.

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%, so the description must carry the load and it only half does. It explains the semantics of 'audio' (string vs null removal) and 'words' (full replacement, not patch), but says nothing about 'revision' (apparently a version/optimistic-lock token) or 'projectId', both required for a correct call.

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 leads with a specific verb and resource: 'Attach imported narration and/or aligned words.' An agent immediately knows this binds audio and word-timing data to a reel. It does not differentiate itself from any of the ~20 reels_* siblings (e.g. reels_import_asset, which supplies the 'imported' asset referenced here), which keeps it below 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?

There is no when-to-use guidance, no prerequisite chain (the phrase 'imported narration' implies an asset must exist first, but never says so), and no mention of when to call this versus reels_edit_entity or reels_timeline. The null-audio case is the only conditional behavior stated.

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