get_text

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

With no annotations, the description carries the full burden, and it delivers: it explains effective-style reporting, live vs file style naming differences, textbox entry behavior (source 'textbox', box_index used by set_textbox_text, body indices untouched), and equation invisibility. This is substantial behavioral insight beyond the raw schema.

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?

Every sentence carries necessary information: return shape, slicing semantics, textboxes, live-mode behavior, and the equation exclusion. It is dense but efficient, with no filler or tautology. The most important information appears first.

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 an output schema exists, return value details need not be repeated. The description covers non-obvious behaviors thoroughly. Minor gaps remain, such as how 'contains' matching works (case-sensitivity, substring) and exact behavior of the 'live' parameter, but these are edge cases rather than central calling requirements.

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 explain parameters itself. It does explain start/end slicing (0-based, exclusive), contains filtering, include_textboxes semantics, and live vs file behavior well. However, the 'live' parameter's accepted values and interaction with 'auto' are not fully specified, and file_path is left to obvious inference.

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 opens with a specific verb+resource: 'Read body paragraphs'. It also explains the return shape and explicitly notes that equations are not included, pointing to list_equations. This clearly distinguishes it from siblings like get_document_info or list_equations even without naming them all.

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 gives clear context: file-mode vs live mode, and the file-mode-only condition for include_textboxes. It also explicitly routes equation needs to list_equations. However, it does not state when to prefer alternatives like get_outline or find_text, so it stops short of full when/when-not coverage.

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