scan_document

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

With no annotations provided, the description carries the burden of behavioral disclosure. It reveals that the tool caches the document and writes stable UUID labels, and warns against repeated calls. However, it does not disclose what happens if called multiple times, whether existing labels are overwritten, or the exact cost/impact of the scan. Still, it adds meaningful context beyond the schema.

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 two sentences with no fluff. It front-loads the core action and follows with essential usage guidance. Every word earns its place, making it both concise and well-structured.

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 4-parameter tool with no output schema, the description covers the core workflow: scan once, cache, then use execute_batch. It introduces the 'session Document Model cache' concept and clarifies the tool's role in the edit workflow. However, it does not explain how to access the cache later (e.g., via get_document_model) or describe return values, leaving minor gaps.

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 schema description coverage is 75%, so the description does not need to compensate heavily. The description mentions 'write stable mcp:<uuid> labels' which aligns with the writeUuids parameter, but does not provide additional semantic detail for depth, timeoutSec, or captureSnapshot beyond what the schema already offers. Baseline 3 is appropriate.

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 clearly states the tool scans the active InDesign document into the session Document Model cache and writes mcp:<uuid> labels, distinguishing it from siblings like refresh_document and get_document_model. It also specifies the timing ('ONCE per session before planning edits'), making the purpose 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 explicitly instructs to call it once per session before planning edits, and directs the agent to use execute_batch for subsequent operations rather than repeated scans. This provides clear when-to-use and when-not-to-use guidance with an explicit alternative.

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