set_cell

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

With no annotations, the description carries the full burden of behavioral disclosure, and it excels: it reveals formula normalization, no literal escape for '=' strings, recalculation flags, hazardous-workbook refusal, backup rotation behavior, atomic verified saves with rollback, and the Excel-open lockout. This is far more transparent than typical tool descriptions.

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 not wasteful; every clause contributes meaningful behavioral information and the core action is front-loaded. The final sentence packs several distinct behaviors together, but nothing is fluff, so the length is justified for the tool's complexity.

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?

For a complex mutation tool with no annotations, this is a very complete description: it covers formula behavior, backup strategy, persistence safety, and failure conditions, and an output schema exists so return details are unnecessary. Minor gaps, such as how location objects are constructed and explicit path/sheet semantics, keep it from being fully comprehensive.

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 0%, but the description compensates for most non-obvious parameters: value's formula/literal semantics, backup's rotation toggle, allow_loss's safety bypass, and location as the addressing object. It does not fully explain path, sheet, or the exact shape of the location object, leaving some burden on the schema property names.

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 pair: "Write a single cell addressed by a location object." It clearly limits the action to a single cell, which distinguishes it from range-writing siblings like write_range or set_cells, and the additional formula-vs-literal detail makes the purpose even more precise.

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 contextual guidance for when this tool is appropriate: for writing a single cell, with explicit conditions around hazardous workbooks and Excel lockout. However, it never names alternative tools for multi-cell writes or formula-specific writes, so exclusions are implied rather than stated.

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