table_get

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

Annotations only declare readOnlyHint=true, so the description carries most of the behavioral burden and does so well: numbering rules for nested tables, the fact that an empty w:tbl still consumes a number, and story-scoped numbering. It adds no error or failure semantics (e.g., what happens for an out-of-range table number), which keeps it from a 5.

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?

Two dense sentences with no filler; the return shape is front-loaded and the numbering rules follow immediately. Every clause conveys a constraint the agent could act on.

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?

With no output schema, the description correctly takes on the return contract — grid rows, per-cell first grid column, gridSpan, vmerge states, and paragraph addresses — plus the numbering semantics needed to interpret `table` and `at`. Nothing essential for a correct call 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?

Schema description coverage is 100%, and the schema's own descriptions largely duplicate the description's story-numbering explanation for `at` and `table`. The description adds the returned-grid shape but no new syntax, formats, or edge-case meaning for the three parameters, so the baseline 3 is appropriate.

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 the exact resource and its contents ('One table's grid: its rows of cells') and enumerates the per-cell fields (col, span, vmerge, paragraph addresses), so an agent can immediately tell this is a read of a table structure rather than of paragraphs (para_get) or a row mutation (table_row_delete). Scope limits are stated, including that text-box/DrawingML tables are not counted.

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?

It gives useful addressing context ('table numbers the main story only; at works in any story'), which implies how to reach non-main-story tables, but it never states at a tool level when to pick table_get over siblings like para_get or outline, nor any exclusions. Usage is inferable rather than spelled out.

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