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

Annotations already set readOnlyHint=false, destructiveHint=false, idempotentHint=false, so the safety profile is given. The description adds real behavioral context (deterministic, ground truth, explicit null/unknown provenance, duplicate/misfile detection) and even describes the result payload. But given the tool is named 'audit' yet declares readOnlyHint=false, the description never clarifies whether the call mutates project state - a notable gap.

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 important scoping constraint is front-loaded, which is good. But the body is dense, jargon-heavy and hard to parse ('the 1-2 budget of a talking short', 'literal pun, opening whoosh'), packing domain detail that an agent selecting the tool does not need. Sizeable trimming is possible without losing selection-relevant signal.

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 carries the return-value burden and does describe the audit payload in detail (roles, provenance, rights signals, SHA-256, placement checks). It is nearly complete for an inspection tool, with the only real hole being the unexplained mutation/readOnly semantics.

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% and there is a single required parameter, so the schema already documents project_id fully (including the 'never guess the active project' warning). The description's 'acts only on the explicit project_id' restates the same scoping constraint, adding no syntax or format beyond the schema. Baseline 3 applies.

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 names a specific verb+resource: a deterministic audit of the current EDL's authored music/voiceover/SFX roles, files, windows, offsets, gains, ducking and mastering. An agent can distinguish it from audit_captions/audit_motion by the 'audio mix' scope. It stops short of explicitly contrasting siblings, keeping it at 4 rather than 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?

It positions itself against the rendered 'AUDIO CHECK' preview ('This state is ground truth... without relabeling roles'), which implies when to prefer authoritative role inspection over rendered measurement. However there is no explicit when-to-use/when-not guidance against the other audit_* tools, so usage is only implied.

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