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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=true. The description adds that the crop is content-aware (tracks speaker/action), which explains why output is non-deterministic and thus supports the idempotentHint=false annotation. It does not disclose that this is presumably a long-running job returning a job_id, whether it costs credits, or whether the source video is retained — meaningful gaps for a compute-heavy mutation.

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?

A single front-loaded sentence with the verb, resource, and target format before the tracking detail. No filler or redundancy.

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?

Mission-critical context is present: it states all three parameters are optional with empty-string defaults (missing in description but present in schema), and neither source defaults to another, so a caller can leave both unset or empty. However, the lack of any async/job, cost, or resize_video differentiation detail leaves real gaps for a moderately complex AI tool.

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%, including enum values, defaults, and the source_id vs video_url exclusivity, so the schema carries the parameter burden. The description only echoes the aspect-ratio concept and adds no semantics about default format behavior or what happens when both source inputs are empty (all params optional, defaults '').

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?

Names a specific verb ('Reframes') and resource ('a video') plus the concrete outcome (a target aspect ratio such as 9:16) and the mechanism (auto-following speaker/action). It is clearly not a plain convert or compress tool. However, a sibling named resize_video exists and the description never distinguishes aspect-ratio reframing with subject tracking from resizing, leaving real ambiguity between the two.

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 'landscape to 9:16 vertical while following the speaker' phrasing implies the use case (social/vertical reformatting with content tracking), but there is no explicit when-to-use, when-not-to-use, or pointer to resize_video. Guidance is inferable rather than stated.

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