Analyze Loudness

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

Discloses the tool's non-mutating scope beyond what the annotations provide: no audio normalization and no changes to the Premiere project, which is valuable safety information for an agent, especially since the annotations carry only negative hints (readOnlyHint=false, idempotentHint=false). There is a minor tension between 'Analysis only' and readOnlyHint=false, but the specific caveats prevent it from being a hard contradiction.

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?

Two sentences with zero filler: the core function and measurement units are front-loaded, and the critical 'analysis only' caveat lands immediately after. Every clause earns its place.

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 an output schema present and full parameter coverage, the description only needs to cover selection criteria and side effects, which it largely does. Missing: no explicit guidance on choosing between media_path and project_item_id when both are provided, and no explicit routing to normalize_loudness_file or verify_delivery_file — minor gaps for an otherwise complete definition.

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?

The input schema documents all 5 parameters at 100% coverage, so the schema carries the documentation burden and the baseline of 3 applies. The description connects to measurement outputs (LUFS/LU/dBFS) but adds no syntax, format, or relationship details about parameters like target_lufs or tolerance_lu beyond what the schema already states.

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?

States a specific verb ('Measure') with precise resources: integrated loudness (LUFS), loudness range (LU), and true peak (dBFS) from a local media file via FFmpeg's EBU R128 filter. The closing clause explicitly distinguishes it from the mutating sibling normalize_loudness_file, so an agent can tell them apart at a glance.

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?

Provides a clear exclusion — 'it does not normalize audio or change Premiere' — which tells the agent this is the wrong tool for normalization or project-modification tasks. However, it doesn't explicitly name the alternative (normalize_loudness_file) or offer affirmative when-to-use guidance relative to nearby siblings like verify_delivery_file.

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