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

Annotations declare non-read-only, non-idempotent, non-destructive, so safety is largely covered. The description goes beyond them with real operational context: ~5.7 credits per minute billed by the second, an fps floor/ceiling expectation, and a required skill load – all useful for a costly 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?

Dense and mostly front-loaded: the core action leads, followed by constraints and cost. Survives on few sentences with no filler, though the first sentence's clunky construction slightly hurts readability.

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?

No output schema, so the description should ideally note that this starts a job whose result is awaited later, and it never explains the label parameter. It does cover cost and prerequisites, which is the most important missing context for a paid job-starting 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 only 13%, so the description carries heavy burden. It usefully defines 'at' (source time), the box ordering constraint (x1>x0, y1>y0), fps (normally 8), and the source-time range, but leaves assetId, label, and the box coordinate frame unaddressed.

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+resource: 'Track an object seeded by a source-pixel box at source time at.' The 'source-pixel box' qualifier separates it from track_points, track_faces, and track_detection. The phrasing is slightly garbled ('at source time at'), which keeps it 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?

Gives a prerequisite ('Load builtin-object-tracking first') and operational constraints ('do not lower fps or split a long clip'), but never says when to prefer this over the sibling trackers or what conditions select it.

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