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

Annotations only declare the safety profile (readOnly=false, idempotent=false, destructive=false); the description adds genuinely new context: credit cost ('about 5.7 credits a minute... billed by the second') and quality constraints that affect output. It does not disclose job duration or async behavior, so it stops short of a 5.

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?

Four dense sentences, front-loaded with the operation itself, then constraints, cost, and prerequisite. Little waste, though the opening sentence's 'at source time at' phrasing is awkward and slightly impedes 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?

For an 8-required-param, non-readonly call with no output schema, the description covers cost, prerequisite skill, and operational constraints well. However it never addresses what happens after the call — job/wait_for_jobs semantics or how the resulting track is later read (e.g. read_points) — leaving a real gap for an agent planning a workflow.

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% (just projectId), so the description must carry the burden — and it explains the meaning of `at` (source time), `points` (source-pixel seeds), `fps` (normally 8, and the reason not to lower it), and the startTime/endTime range. `label` and `assetId` are left implicit, which is a minor residual gap.

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 and resource ('Track an object seeded by one or more source-pixel points'), which meaningfully distinguishes it from box-, face-, or detection-based tracking siblings. The phrase 'at source time at' is garbled and partially blurs the intent, and no sibling is named for contrast, keeping it below 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?

Provides clear context ('Specify source-time range and fps (normally 8)') plus explicit exclusions ('do not lower fps or split a long clip') and a hard prerequisite ('Load builtin-object-tracking first'). It never explicitly routes the agent away from track_box/track_faces/track_detection, so the when-to-use-vs-alternatives guidance is only partial.

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