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

Goes well beyond the readOnly/idempotent/non-destructive annotations: it describes the exact result content (points in target space plus film, film_norm, source, source second and frame, in-frame flags with reasons, chain), states that 'Free' calls cost nothing, and discloses partial-failure semantics — a geometry that cannot convert returns ok false with a reason while the others still convert.

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?

The core capability is front-loaded in the first sentence and every subsequent sentence carries real information (examples, return shape, failure behavior). It is somewhat run-on and the example list is dense, but there is no filler.

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?

Five required parameters with a deeply nested geometry object and no output schema, so the description must carry the return-value burden — and it does, describing the result fields, partial failures, and the transform chain. Nothing essential to invoking or interpreting the call 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 coverage is 100%, so the baseline is 3; the description adds meaning on top by tying spaces to their qualifiers (preview space needs previewId, surface needs trackId) and explaining time fallback ('A preview point uses its tile's time'). It does not enumerate the detail levels or tile semantics beyond what the schema already states.

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?

Opens with a specific verb and resource: 'Convert points, boxes, quads, lines or polygons between coordinate spaces at a timeline second'. It also scopes the transform chain (fit/crop, transforms, groups, camera, preview) which separates it cleanly from siblings like track_points, read_points, and snap.

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?

Explicitly says 'Use it instead of converting by hand' and supplies four worked scenarios (preview point to source, source pixel to film, surface corners to film, UV to film for a label) that make the use case concrete. It stops short of stating when not to use it or naming a competing sibling for coordinate work.

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