Normalize loudness

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

With no annotations provided, the description must carry the full burden. It adds a key behavioral fact ('Video is untouched') and explains the loudness standard, but it does not disclose whether the original file is preserved, what the tool returns, or any potential side effects like quality changes. This is acceptable but not comprehensive.

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 two sentences, each earning its place. It starts with the action and outcome, then adds a crucial caveat. No filler or redundancy.

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?

The description covers the core purpose and a key limitation (video untouched), but with no output schema and no annotations, it should mention what the tool returns and whether the input is modified. The output_path parameter hints at a new file, but the description doesn't explicitly confirm non-destructive behavior or result format. There is room for improvement.

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%, so the schema already documents all parameters. The description does not add meaning to input_path or output_path beyond the schema; it only broadly frames the tool's purpose. The baseline of 3 applies here.

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 clearly states a specific verb ('Normalize') and resource ('audio') with a concrete outcome ('broadcast-standard loudness (EBU R128)'). It also distinguishes the tool from siblings by noting that video is untouched, which is not obvious from the name alone.

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 some contextual use cases ('podcast/social-media levels', 'fixes too-quiet or wildly varying audio') but does not explicitly mention when to prefer this over sibling tools like adjust_volume, nor does it state exclusions. The guidance is implied rather than explicit.

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