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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it returns MCP images (not just data), renders JPEG stills, and uses the exact platform frame. This goes beyond what annotations provide.

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?

One sentence, front-loaded with the action and purpose. Every phrase earns its place: 'JPEG stills', 'compiled carousel', 'exact platform frame', 'MCP images', 'inspect chips on the real slides'. No wasted words.

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?

The tool has an output schema (MCP images), so return values are covered. The description explains the purpose and output format. It could mention that the carousel must be compiled first (prerequisite), but the word 'compiled' implies this. For a read-only preview tool with rich annotations, this is nearly complete.

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 25% (only projectId has a description, and it's just 'UUID string'). The description mentions 'compiled carousel' and 'platform frame' which hints at projectId and chrome, but doesn't explain slideIndexes or workspaceId. The chrome enum is self-explanatory, but slideIndexes semantics (which slides to render) are not described. Baseline 3 is appropriate since the description adds some context but doesn't fully compensate for the low schema coverage.

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 states a specific verb ('Render'), a specific resource ('compiled carousel'), and the exact purpose ('inspect chips on the real slides'). It clearly distinguishes this from sibling tools like carousels_compile or carousels_get by focusing on previewing rendered stills as MCP images.

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 implies this is for inspecting a compiled carousel before/after compilation, and the 'exact platform frame' phrasing signals it's for platform-specific visual verification. It doesn't explicitly name alternatives or exclusions, but the context is clear enough for an agent to select it over compile/get tools.

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