add_field

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

With no annotations, the description bears full burden. It explains the coordinate system (percentages, top-left origin), the meaning of align and vertical_align parameters, and how values are positioned. However, it omits behavioral details like what happens on duplicate names, field_type/drop behavior, or page_index scope.

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 efficient: four sentences that front-load the purpose, then add coordinate and alignment details. No redundancy or filler.

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 9 parameters, no schema descriptions, no annotations, and an existing output schema? the description covers the most critical input semantics but omits name, field_type, and page_index. It also does not reference the output schema. There are clear gaps for a tool with this complexity.

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%, so description must compensate. It explains x,y,w,h as percentages with top-left origin, and align/vertical_align with value constraints. But name, field_type, and page_index are not explained, leaving gaps for 4 of 9 parameters.

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 adds a field that the detector missed (false negative), which is a specific verb+resource. It distinguishes from siblings like update_field (modify existing) and remove_field (delete) by focusing on adding missed detections.

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 implies usage for adding missed fields based on detector output, but does not explicitly state when not to use it or mention alternatives among the sibling tools. The context is clear but guidance is implicit.

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