Edit table rows and columns

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

Beyond the destructiveHint=true annotation, the description discloses that deleting a row/column removes ALL its content and that the content is unrecoverable. It also warns that deletions shift every later index in the document, requiring a re-read. This is exactly the kind of behavioral context the annotation alone does not provide.

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 dense but efficient; every sentence carries essential operational information: how the table is addressed, how insert actions behave, how delete actions are destructive, index defaults, and the re-read warning. It avoids fluff while front-loading the core purpose.

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 — four actions, eight parameters, destructive behavior, and index-shifting side effects — the description covers everything needed to invoke it correctly: addressing, defaults, insertion direction, irreversibility, and the need to re-read after deletion. No output schema exists, but return values are not necessary for correct invocation here.

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 coverage is 100%, but the description adds meaningful cross-parameter semantics: it explains that row_index/column_index identify the anchor cell, that insert_below and insert_right default to true, and that table_start_index comes specifically from read_document_text/get_document. This goes well beyond the individual property descriptions in the schema.

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 clearly states a specific verb and resource: 'Inserts or deletes a row/column of an existing table.' This differentiates it from sibling insert_table, which creates new tables, by explicitly scoping to existing tables and enumerating the four supported 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?

It provides clear procedural context: the table is addressed via table_start_index from read_document_text, indices are 0-based, and the agent is told to re-read before further edits after deletions. It does not explicitly name alternatives or state when not to use this tool, but the guidance is sufficiently clear to route an agent correctly.

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