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

Beyond the readOnly/openWorld/idempotent annotations, the description adds significant non-obvious behavior: extraction statuses ('exact', 'recovered', 'needs_review') explain whether objects were consolidated, applied, or preserved with a warning. It also warns that grid.tiles[].url is 'a rebuilt presentation layout, not the geometry used to cut the model output' and tells agents to read the background block back when aspectRatio was unset. This prevents misinterpreting output as original file structure.

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 description is front-loaded with the core result ('One asset with its revision iterations') and then systematically covers variants, extraction statuses, grid semantics, and backgrounds. Every sentence adds meaningful detail, but the dense single-paragraph structure with many clauses makes it slightly harder to scan at a glance. Still, there is no filler or repetition.

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?

There is no output schema, so the description must carry the return-shape burden and does ensure the agent knows what to expect: Material typed material block, legacy seamless metadata, Generation exact, generationPlan/extraction statuses, grid tiles as transparent PNGs, and the background block for confirming aspect ratio. It also notes legacy asset behavior when extraction is absent. That is enough to make the tool call correctly without an output schema.

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?

The input schema already provides a description for assetId as 'Asset id or slug', and schema coverage is 100%. The tool description only restates 'Accepts the asset id OR its slug' without adding constraints, formats, or examples. Since the schema carries the full parameter meaning, no additional parameter semantics are needed and 3 is the baseline.

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 description explicitly states 'One asset with its revision iterations and typed animation projection', naming a specific verb/resource combination and its main output. It also makes clear the lookup uses 'asset id OR its slug', which distinguishes this tool from sibling getters like get_map or get_character and from list_assets. This is specific and unambiguous.

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?

The description never explicitly says 'use this for a single asset lookup; use list_assets to enumerate or other getters for other resources'. The intended use is only implied by the phrase 'One asset' and 'Accepts the asset id OR its slug'. Conditional clarifications (Material vs legacy vs Generation Contract) describe output semantics, not when to choose this over a sibling, so there is no explicit when-not guidance.

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