get_table

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

No annotations are provided, so the description carries the full burden. It explicitly states 'Read-only', declares that it reads 'the last-saved state of a document open in Word', and describes the returned data (cell text, merge map, column widths). This gives an agent a clear safety and freshness profile beyond the tool name.

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 information-dense and front-loaded with the core purpose, then addresses parameters and behavior. The final line about the media-forms pack adds some redundancy but also covers row/column surgery, styling, and sort, so it earns some place. Overall, there is little wasted text.

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?

This is a relatively complex tool with nested-table addressing and a 0% schema description coverage, and the description handles that complexity well. It covers read-only behavior, saved-state semantics, table indexing, nested access, and related tools. The output schema exists, so the description does not need to detail the return shape further. Minor gaps like file_path syntax are acceptable.

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 does well for table_index, explaining 0-based indexing among body-level tables in document order, and for nested, specifying its shape and default behavior. file_path is not elaborated, but it is self-evident for this family of document tools.

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 and resource: 'Read one table in full', and details exactly what is returned (cell text, merge map, column widths). It clearly distinguishes itself from write/reshape tools by naming set_cells and modify_table_structure as the alternatives for those actions.

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 for when to use the tool: when the full content and structure of a table is needed. It explicitly points to set_cells for writing values and modify_table_structure for reshaping, which helps an agent avoid misusing this read-only tool. It does not explicitly enumerate all non-use cases among read siblings, but the guidance is strong.

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