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

The description adds valuable behavioral details beyond the annotations: cost per call (1 credit), temporary download link validity (15 minutes), and the JSON body requirement for image watermarks. It also clarifies the default overlay behavior (every page). This goes beyond readOnlyHint/idempotentHint/destructiveHint and is not contradictory.

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 concise (three sentences) and front-loaded with the action. It efficiently includes cost, link validity, and the JSON body note without unnecessary elaboration. Slightly dense but well-structured and readable.

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 complexity (10 parameters), the description covers the key operational aspects: cost, return format (download link), and the JSON body constraint for images. It does not explicitly state that the output is a PDF, but that is implied. The schema handles parameter details, so the description is adequate for correct invocation.

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 provides descriptions for all 10 parameters (100% coverage), including max text length, image format, scale, opacity, and position. The description repeats some of these (e.g., max 200 characters, PNG/JPEG), but adds no extra parameter semantics. The baseline score of 3 is appropriate because the schema carries the parameter documentation.

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 action: 'Add a text or image watermark to a PDF.' It specifies the resource (PDF) and the two watermark types, and notes the overlay behavior (every page or specified pages). This distinguishes it from siblings like pdf_to_images or merge_pdfs, which have different purposes.

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 provides useful context: image watermarks require a JSON body, the call costs 1 credit, and it returns a temporary link. However, it does not explicitly contrast this tool with alternatives or state when not to use it. The tool name and role carry most of the load for selecting it.

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