Inspect a video or audio file

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

Annotations already declare readOnly/non-destructive/non-openWorld, so the bar is lower, yet the description adds real value: the budgetUsd hold-and-release cost mechanic (default 2, max 10), the write-scope auth requirement, and the fact that it returns an actual filmstrip and timestamped words. The "needs the write scope" note sits oddly beside readOnlyHint but is an auth disclosure rather than a behavioral 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?

Purpose is front-loaded, the capability enumeration is dense but each item is distinct and useful, and the closing sentences carry the sequencing, cost, and auth facts with zero filler. Appropriately sized for a seven-parameter tool.

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 the description need not explain return values, yet it still covers purpose, sequencing, cost, and auth. The only friction is the write-scope note against a readOnly annotation, which a caller might read as ambiguous but not contradictory.

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%, so the schema already documents all seven parameters including defaults and the max:24 frame_count bound. The description restates budgetUsd's default/max and hints at the filmstrip-vs-frames tradeoff, adding only marginal meaning beyond the structured fields.

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?

Specific verb plus resource (look at / inspect a video or audio file in the media library) followed by an explicit enumeration of what it exposes: duration, size, frame rate, loudness, filmstrip, chosen frames, waveform, and time-aligned transcript. It is clearly distinguishable from sibling write tools like edit_footage, which it explicitly references.

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?

"Read it before edit_footage" gives concrete sequencing guidance against a named sibling, and media_key's schema text points at media_library as the source of the key. There is no explicit when-not guidance (e.g., for still images or already-transcribed clips beyond the transcript flag), so it stops short of full alternative routing.

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