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

Annotations already declare readOnlyHint/idempotentHint/closed-world, and the description reinforces this with concrete behavioral facts: no drafts, files, or server sessions are created (stateless, pure computation), and unknown physical values are preserved as symbols rather than fabricated. It also discloses the return shape (document + web link), which annotations cannot convey. It stops short of describing validation failures or error behavior.

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?

Two dense sentences with no filler; the input requirement and output are front-loaded, followed by the side-effect and symbol-preservation constraints. Every clause carries information, though the phrasing is terse enough that some clauses need unpacking.

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 deeply nested schema with no output schema, the description covers the essential contract: what to pass, what is produced, and that no persistent state is involved. Given the complexity of the nested SceneSpec, a brief note on validation/error reporting would have made it fully self-sufficient.

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?

Top-level schema description coverage is 0%, so the description must compensate for the two parameters. It meaningfully constrains `spec` ('complete SceneSpec', relative-relationship based, unknown values kept symbolic) but says nothing about the optional `name` parameter, 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?

States a specific verb pair and resource: generate and check a scene from a complete SceneSpec, and names the outputs (document plus a small-scene web link). It is clear what the tool does, though it never distinguishes itself from neighbors like preview_scene or export_scene, which also produce scene artifacts.

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?

Usage is only implied: '传入完整 SceneSpec' signals the prerequisite that a fully-formed spec must already exist (presumably from get_build_spec), but there is no explicit when-to-use versus preview_scene/review_scene, and no statement of when not to use it.

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