Audit Timeline Health

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and non-openWorld, so the safety profile is largely covered. The description adds genuinely new behavioral context: 'Local-only', implying no network/media fetch, and 'never changes Premiere', plus the scoring and fix-route output shape. It stops short of noting runtime or input-size limits for large snapshots.

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?

Front-loaded with the verb 'Audit' and the target, then the defect enumeration, then outputs, then the safety note. The eleven-item check list is long but each entry is a concrete, non-redundant check that helps an agent predict coverage. Slight verbosity in the enumeration keeps it from a 5.

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?

Given a deeply nested snapshot schema at 100% coverage and an existing output schema, the description supplies the remaining context an agent needs: scope (single snapshot), the breadth of detection, the output shape in prose, and the local read-only guarantee. Missing only comparison with adjacent audit tools, but that is a usage-guideline gap rather than a completeness gap.

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%, and every one of the seven parameters (frame_rate, gap_min_frames, max_speed_percent, expected_frame_rate, flash_frame_max_frames, expected_duration_seconds, snapshot) is documented with defaults and ranges in the schema. The description adds no semantics beyond what the schema already provides, so the 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?

States a specific verb (audit) and resource (one sequence snapshot), then enumerates the eleven defect classes it detects (flash frames, gaps, overlaps, disabled clips, repeated shots, video without audio, extreme speed, invalid times, empty tracks, leading black, trailing gaps) and the outputs (0..100 score, findings with timecodes, fix routes). This is far more specific than the name alone and distinguishes it from read-only inspectors like inspect_sequence_review_report or diff_sequence_snapshots.

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?

The description implies usage by specifying that it audits 'one sequence snapshot', which signals the input precondition, but it names no alternatives and gives no explicit when-to-use or when-not-to-use guidance versus closely related siblings such as inspect_sequence_review_report, analyze_video_qc, or diff_sequence_snapshots. Usage is inferable but not spelled out.

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