Inspect Doc Structure

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

The annotations already mark this as readOnly, idempotent, and non-destructive. The description adds substantive behavioral context beyond those hints: it defines total_length as the maximum safe insertion index, warns against inventing segment IDs, and explains the conditional behavior of tabs in the output. It makes the tool's inspection semantics and safe usage bounds explicit.

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 lengthy but well-organized into labeled sections, bullets, and numbered steps, which makes the complexity navigable. It front-loads the core purpose and critical usage warning, and most sections earn their place by conveying actionable workflow detail. Some redundancy exists between the 'CRITICAL FOR TABLE OPERATIONS' callout and the repeated workflow steps, but it does not become noise.

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 tool's complexity and the presence of an output schema, the description is exceptionally complete. It covers not just what the tool returns but how to consume those outputs in real workflows (table insertion indices, formatting ranges, header/footer segment IDs). Nothing an agent needs to call this tool correctly is missing.

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?

Input schema covers 100% of parameters with descriptions, so the baseline is 3. The description adds extra meaning by explaining how the detailed parameter changes the output (elements with start_index/end_index and text_preview) and that tab_id controls whether a list of tabs is returned. This goes beyond the schema's minimal parameter descriptions.

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 uses a clear verb+resource combination: 'inspect' + 'document structure', and goes further to state the primary purpose: finding safe insertion points and understanding layout. It differentiates itself from siblings like debug_table_structure by emphasizing safe index discovery and document-wide structure inspection, not low-level table debugging.

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?

Explicit usage guidance is provided in multiple forms: a 'USE THIS FOR' list, a 'CRITICAL FOR TABLE OPERATIONS' mandate to call before creating tables, and workflow steps for table insertion, formatting, and header/footer editing. It also names an alternative (update_doc_headers_footers) for ordinary header/footer text, drawing a clear when-to-use versus when-not-to-use boundary.

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