sort_range

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

With no annotations, the description carries full behavioral disclosure, and it does so thoroughly. It explicitly describes mutation, formula reference shifts, cached-value comparison with warnings, hidden-row pinning, auto-backup as undo, atomic saves, and refusal conditions. This is far beyond minimal disclosure.

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 adds meaningful behavior, with the primary action front-loaded, followed by key semantics and then edge cases and safety. There is no filler, and the high information density remains readable.

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 8-parameter mutation tool with no annotations, the description is unusually complete: it covers mutability, key semantics, formula behavior, hidden rows, backup/undo, and concurrency refusal. The only gaps are optional parameters sheet and verify_com, which are low-risk and not central to correct sorting calls.

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?

At 0% schema description coverage, the description compensates well for the most complex parameter (keys), explaining column identification via header name, letter, or index, asc/desc order, and tie-breaking. It also clarifies has_header, backup, and allow_loss, but leaves sheet and verify_com unexplained and only implicitly covers location through 'range or table body'.

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?

Clearly states the specific action: sorting a range or table body by one or more keys and writing rows back reordered. This distinguishes it from sibling read/write/query operations, and the detailed key-structure description leaves no doubt about what the tool does.

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?

Provides strong operational context: key formats, tie-breaking, header behavior, Excel-consistent handling of formulas and hidden rows, and explicit preconditions like allow_loss for hazardous workbooks and refusal while open in Excel. It does not name alternative tools, but no sibling performs sorting, so the context is sufficient.

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