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

Annotations declare a non-idempotent write that is neither destructive nor open-world; the description adds genuinely useful context beyond that by stating the call is project-scoped, returns the project identity alongside the result, and writes everything in one atomic batch. It does not contradict the annotations, but it omits what gets mutated in the scene or any permission/precondition detail.

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 PROJECT-SCOPED clause is correctly front-loaded, but the sentence is a run-on that spends most of its length on eight example 'where' phrases, which is repetitive and crowds out substantive parameter explanation. The examples do illustrate the expected free-text format, so they are not pure waste.

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 9-parameter, non-idempotent write with no output schema and only 11% schema coverage, the description should explain the placement coordinate parameters and the result shape. It covers scope and the `where` phrasing and notes that the project identity is returned, but leaves most parameters and the mutation semantics unexplained.

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 11% (only project_id is documented), so the description must carry the burden and only partially does. It usefully explains `where` as free-text phrases and hints at pairing box+t and quad+t, and it implies motion_id vs text are alternatives, but start, end, text, and motion_id are never defined and no format or constraint is given for box/quad.

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?

The verb is 'Places' and the resource is a spatially positioned motion_id or text, which is a real action, but the resource is vague (the 'world' concept is never explained) and the purpose is buried under a long list of example phrases. It gestures at differentiation from siblings like remove_world/look_at_world but never states it, so an agent must infer what 'the world' is.

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?

There is no explicit when-to-use versus alternatives (e.g. pin_to_plane, add_text_behind, select_object, track_point). The only usage instruction is how to phrase the `where` argument, which is parameter guidance, not tool-selection guidance.

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