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

Annotations are all false and convey little, so the description productively adds the critical runtime trait: the tool cannot execute on this endpoint and why. It doesn't describe side effects, but since invocation is blocked, the most relevant behavior is disclosed.

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?

Two sentences with zero filler; the critical unavailability message is front-loaded and the fallback path is stated compactly. The URL is necessary for the alternative and not excessive.

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 that is unavailable on this endpoint, the description fully equips the agent: it says not to invoke it, explains why, and supplies the workaround. The rich parameter schema covers the remaining invocation details for a local install.

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?

All six parameters have descriptions in the schema, including defaults, constraints, enums, and effects, so the schema carries the parameter-load. The description adds no parameter-level information, matching the baseline-3 case.

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 title and the repeated word 'watermark' make the operation clear, but the description itself never states 'adds a text watermark to an image' as an active definition. It instead leads with unavailability, so the purpose is inferable rather than explicitly specified.

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 the agent not to use this tool on the hosted endpoint, gives the technical reason (missing bitmap font files), and names concrete alternatives: a local install with a download URL or uploading an already-watermarked image. This is exemplary when-not-to-use guidance.

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