insert_watermark

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

No annotations are provided, so the description bears the full burden of disclosing behavior. It describes the placement in the default header and the VML structure, but does not mention potential side effects (e.g., overwriting existing header content, document modification impact, or error conditions). Some behavioral context is given, but not comprehensive.

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 moderately concise but includes detailed internal VML formatting that may not be essential for tool selection. It is front-loaded with the main purpose, but the length could be reduced without losing key information. Every sentence provides value, but some technical details are verbose.

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 output schema exists (not shown), the description does not need to explain return values. However, it lacks guidance on edge cases (e.g., what happens if the document has no header, or if text is empty). The tool's behavior is adequately described for common use but incomplete for all scenarios.

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 coverage is 0%, yet the description thoroughly explains each parameter: 'text' as watermark text (e.g., 'DRAFT'), 'diagonal' with default true and orientation behavior, and 'document_handle' for concurrent session isolation. This adds significant meaning beyond the schema's types and defaults.

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's purpose: 'Insert a VML watermark into the document's default header.' It specifies the mechanism (placing a <v:shape> with <v:textpath>) and is distinct from sibling tools like 'remove_watermark'. The verb 'insert' and resource 'watermark' are specific and 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 explains the watermark pattern and default orientation but does not explicitly state when to use this tool versus alternatives like 'remove_watermark' or other insert tools. There is no guidance on prerequisites or context (e.g., whether a header must exist). Usage is implied but not explicitly delineated.

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