watermark

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does so well by explicitly stating that the source file is unchanged, that the label is drawn with an alpha channel for blending, and that it returns the output path and effective position. While it doesn't cover edge cases like invalid file formats or error handling, it covers the essential transmission-pertinent behaviors.

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 wasted words. The first sentence front-loads the core action and the non-destructive write behavior; the second sentence lists configuration options, adds the alpha blending detail, and states the return value. It is concise yet complete.

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 tool with 8 parameters, no annotations, and no output schema, the description provides the essential context: what it does, how it treats the source, what it returns, and a summary of configurable options. It doesn't specify defaults for all parameters, but those are covered in the schema. The description is sufficiently complete for an agent to understand the tool's function and output without ambiguity.

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%, so each parameter already has a description in the schema. The tool description enumerates the parameters (position, color, opacity, font size, padding) and gives an example hex value, but it does not add substantial meaning beyond the schema. It repeats the opacity default but omits other defaults like position and padding, which are available in the schema. This is adequate but not enhancing.

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 ('burn a text label onto an image'), resource (image), and a distinct behavior (writes to a NEW file, source unchanged). This clearly distinguishes it from the sibling 'overlay' tool, which would typically overlay another image. The mention of configurable placement, color, opacity, font size, and padding further narrows the purpose.

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?

Usage is implied — the description makes it obvious this is for adding text watermarks — but it does not explicitly state when to prefer this over the sibling 'overlay' tool or when not to use it. There is no mention of alternatives or exclusion criteria, so the agent must infer from the nature of the tool.

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