add_caption

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

With no annotations provided, the description carries the full burden and does well by disclosing auto-backup behavior, the effect of backup=False, atomic validated saving, and refusal to operate on documents open in Word. It does not detail return values or error behavior, but the output schema covers return structure and the mutation/safety profile is reasonably clear.

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 compact and well-structured: purpose first, then placement/label options, then backup and safety behavior. Every sentence contributes useful information without fluff or repetition.

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 7-parameter schema with 0% parameter-level descriptions and no annotations, the description covers the main behavioral context: what a caption is, where it can be placed, label options, backup semantics, and Word-open refusal. The main gap is that the selection between table_index and after_anchor is not made explicit, which could lead to incorrect invocation.

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 must compensate. It adds meaning for label ('Table | Figure | Equation'), above/below placement, backup behavior, and the anchor concept. However, it leaves key parameters like file_path, table_index, and the relationship between table_index and after_anchor only vaguely implied.

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 names a specific verb ('Insert') and resource ('numbered caption (SEQ field)') and gives the exact format 'Table N: text'. It also specifies placement contexts (above/below a table or at an anchor), which clearly distinguishes this single-caption tool from sibling tools like insert_caption_list or add_cross_reference.

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 when to use the tool: when inserting a single caption for a table, figure, or equation, placed above/below a table or at an anchor. However, it does not explicitly state when not to use it or name alternatives such as insert_caption_list for bulk caption insertion.

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