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

Annotations (readOnlyHint=false, idempotentHint=true) only reveal that this is a non-destructive write. The description adds substantial context: it returns a fact receipt, requires polling get_media_facts, that 'failed is terminal', and that existing pending/ready facts are reused without another charge. That cost and async-state detail goes well beyond the annotations.

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 in the first clause, and the dense sentences each carry operational information. However it is one long run-on paragraph, and the polling/status instructions at the end are cramped, making it harder to scan than an ideally structured definition.

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?

For a complex async tool with nested body, an output schema, and a cost model, the description covers the full lifecycle: what each kind does, the required/recommended intent, the receipt return, and how to poll until ready. Nothing an agent needs to invoke and follow up correctly is missing.

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 kind and intent. The description nonetheless reinforces the critical semantic that intent is SOURCE time (media trim, not timeline time), which disambiguates a genuinely confusing coordinate space beyond the raw schema text.

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 and resource — preparing a perception artifact (subjectTrack or matte) for an authored edit before sighted review. It clearly enumerates the two artifact kinds and their outcomes, so an agent can distinguish the operation. It doesn't explicitly name sibling tools it competes with, so it stops short of a 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 gives explicit selection criteria: use kind=subjectTrack for face/active-speaker reframing, kind=matte for a behind-subject graphic. It states when intent is required (mattes) versus recommended (subject tracks), and explicitly routes the agent away from the wrong path with 'never accept a preview that silently flattens depth'.

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