prepare_review

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

Discloses that no LLM call is made and describes the return format (review prompt + response_schema). Without annotations, this is helpful but could mention mutability or side effects. The description is straightforward about its non-destructive nature.

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?

Highly concise with two well-structured paragraphs covering purpose, usage, arguments, and return. Uses formatting (bold, bullet-like) to highlight key points. Every sentence adds value without redundancy.

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?

Given the tool's simplicity (2 required params, clear output schema), the description covers all essential aspects: purpose, output format, workflow integration (call ingest_review), and parallelization hint. No gaps are apparent.

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?

Adds crucial details: project_id as 'Target project ID' and slide_index as '1-based slide position'. Since schema had 0% description coverage, this fully clarifies the parameters' meaning and usage.

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 it prepares a design-rule review for ONE slide, distinguishes it from other 'prepare_*' siblings by specifying the review focus and mentioning mechanical lint. It also directs to call ingest_review, clarifying its role in the workflow.

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?

Provides clear instructions: generate review JSON then call ingest_review, and suggests reviewing slides in parallel. Does not explicitly state when not to use or compare to alternatives, but the context implies it's the only tool for this task.

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