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

The description implies a read-only, side-effect-free audit ('deterministic audit', 'ground truth', 'returns'), but annotations set readOnlyHint=false. This is a direct contradiction, and the description provides no clarification about any potential side effects.

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-structured, front-loading the PROJECT-SCOPED constraint and then listing the audit components. Every sentence adds value, though it is slightly long.

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, the description thoroughly explains what is returned (roles, files, provenance, SHA-256, null/unknown handling, duplicate/misfile detection). It is sufficient for an agent to understand the result, though exact formatting is not specified.

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 schema documents project_id, but the description adds crucial guidance: it must be copied from list_projects/open_project/project_state and the active-project pointer is never used. This prevents misuse and goes beyond the schema's generic description.

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 the tool audits the audio mix (music, voiceover, SFX) of the current EDL and enumerates specific attributes (roles, files, windows, offsets, gains, ducking, mastering) plus detection capabilities. It distinguishes itself from sibling audit tools like audit_captions by focusing on the audio mix.

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 notes the tool is project-scoped and returns ground truth, and mentions an alternative (deterministic preview AUDIO CHECK) for measuring rendered mix without relabeling roles. However, it does not explicitly name the alternative tool or provide clear when-to-use versus when-not-to-use conditions.

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