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

The description discloses important destructive behavior beyond the readOnlyHint=false annotation: it replaces every previously transcribed caption while preserving hand-written captions. It also surfaces the provider cost, explains speaker labeling semantics, and notes that speaker_count is 0 when no labels were detected.

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 description is dense but well front-loaded: cost appears first, then the operation, then replacement behavior, speaker semantics, and next steps. Every sentence contributes useful information without repetition.

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 three-parameter mutation tool with no output schema, the description covers the key operational behavior, preservation of manual captions, speaker labeling, and how to inspect results. Nothing essential for correctly invoking or sequencing the tool is missing.

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 coverage is 100%, so the input schema already documents project_id, asset_id, and language. The description adds only minor context about the asset being audio or video and does not elaborate on the language hint, so baseline 3 is appropriate.

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 gives a specific verb and resource ('Transcribe an audio or video asset into word-timed captions'), which is immediately distinguishable from sibling tools. It also states the replacement scope, making the operation's intent unambiguous.

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 clearly directs the agent to read resulting rows with get_transcript and to follow with remove_fillers / remove_silence for cleanup. It does not explicitly compare this tool to alternatives such as studio.replace_transcribed, but the surrounding workflow context is strong.

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