Scene Review

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description adds real value beyond that: the full breadth of the eleven checks and the 0-100 score plus detailed issue list, which tells the agent this is an aggregate audit rather than a single check. It stops short of disclosing cost/runtime, which matters for a tool that runs eleven passes, so 4 rather than 5.

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 scope statement and result shape are front-loaded, and the boundary paragraph earns its space by doing the sibling disambiguation work. No filler sentences.

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?

An output schema exists, so the description needn't spell out return fields, and it correctly limits itself to noting the score-plus-issues shape. The only gap is the absence of any hint about execution cost or latency for a full eleven-check audit, which would help an agent decide between this and the narrower scene_validate.

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 100% and the checks enum options are already documented per-parameter, so the baseline is 3. The description restates the check names (spatial, overlaps, zones, etc.) but adds no syntax, precedence, or cost implications for subsetting checks, and says nothing about the format parameter.

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 (audit/review) and resource (scene) and enumerates all eleven check dimensions it runs, plus the score range it returns. The boundary paragraph explicitly separates it from scene_validate and scene_aesthetics, so the agent can route without opening schemas.

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?

Gives an explicit trigger condition ("after any major scene modification to verify quality") and names the two nearest alternatives with the precise scope each covers. Both when-to-use and when-not-when-to-use are present.

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