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

Annotations cover the safety profile (readOnly=false, destructive=false), and the description adds real behavioral context: it is project-scoped and never guesses the active-project pointer, it returns the project identity, and clear=true detaches. It does not mention idempotency or what happens to existing anchors, but it meaningfully exceeds 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?

A single dense run-on paragraph; the important PROJECT-SCOPED scope note is front-loaded, which is good, but the sentence chain mixes scope, anchor options, and parameter semantics with no structural separation, making it harder to parse than necessary.

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 14-parameter mutation tool with no output schema and 21% schema coverage, the description covers the anchor and a handful of semantics but leaves roughly half the parameters unexplained. The scope and detach behavior are covered, so it is adequate but not complete for the tool's complexity.

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 21%, so the description must carry meaning, and it does explain several parameters (pin's [0.5,1] origin, follow options, occluders, lost=hold|hide|static, clear detaches). However several of the 14 parameters (lock, place, which, offset, shadow, smooth, motion_id) get no coverage in either place, so compensation is only partial.

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?

"Attach a motion graphic to the world (MotionItem.anchor)" gives a specific verb and resource, and enumerates the anchor kinds (face part, head, fingertip, joint, tracked point, object, plane). It does not explicitly name a sibling like pin_to_plane or place_in_world to differentiate, 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?

No statement of when to reach for attach versus the many related siblings (pin_to_plane, place_in_world, set_motion_graphic, track_point). Usage must be inferred from the parameter dump; no exclusions or alternative routing are given.

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