Read Video Scopes

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

The description explicitly asserts 'Read-only', but the annotations set readOnlyHint=false, a direct conflict between the two channels, so this is scored 1 per the contradiction rule. Non-contradictory context (bounded single frame, sampled proxy vs rendered scopes, no mutating side effects implied) is genuinely useful but is undercut by the mismatch.

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 tightly packed sentences with zero filler; the returned metrics lead and the caveat about not being rendered scopes follows. 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, return-value shape need not be described, and the description covers the analytical scope and its fidelity caveat well. The missing piece is any usage boundary or note that the sampled proxy may diverge from Premiere's rendered scopes in specific cases, plus the unresolved read-only conflict.

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%, with media_path ('Existing local video file') and time_seconds ('Source-relative frame time from 0 through 86400 seconds') fully documented in the schema. The description adds only the notion of sampling a single bounded frame, which implies single-frame semantics but gives no additional formatting or range detail. Baseline 3 applies when the schema carries the load.

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 (Read) and a precise set of resources it returns: waveform percentiles, RGB parade percentiles, saturation, and near-black/near-white occupancy from one decoded frame. It also explicitly distinguishes itself from 'Premiere's rendered scopes,' so an agent knows this is a sampled proxy rather than a native scopes read, though no sibling tool is named by name.

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?

Usage is implied rather than stated: the phrase 'one bounded decoded local-media frame' plus 'sampled analytical proxy' tells the agent this is for quick per-frame analysis, not frame-accurate scope rendering. There is no explicit when-to-use/when-not, no prerequisites, and no alternative tool named (e.g., analyze_video_qc, get_graphics_white_luminance).

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