add_cross_reference

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

With no annotations, the description carries the full burden and does it well: Word computes the value on update, auto-backup behavior and the backup=False semantics are explained, save is atomic and validated, and open Word documents are refused. These are exactly the behavioral details an agent needs.

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?

Three dense sentences with no filler. The core purpose is front-loaded, and each sentence adds distinct useful information about semantics, backup behavior, or failure conditions.

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?

The description covers insertion point, kind semantics, field evaluation, backup/save behavior, and a key failure condition. It does not specify matching semantics for after_anchor or prerequisites for to_bookmark, but these are reasonably inferable and an output schema is present.

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 0%, so the description compensates for the two least obvious parameters: kind is explicitly defined and backup's rotation behavior is clarified. The required parameters file_path, after_anchor, and to_bookmark are not formally defined, but their meaning is strongly implied by the description and parameter names.

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?

States a specific action ('Insert a cross-reference field after anchor text') and explains the two kind variants ('page' vs 'text'). This clearly distinguishes it from related tools like insert_field, add_bookmark, or validate_cross_references.

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?

No guidance is given about when to prefer this tool over alternatives such as insert_field, validate_cross_references, or add_bookmark. The refusal of documents open in Word is an operational constraint, not usage guidance.

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