query_range

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

With no annotations provided, the description carries the full burden, and it excels: it declares read-only, explains CACHED vs. recalculated values (uncalculated formulas read as blank), numeric-vs-text comparison coercion, blanks never satisfying ordered comparisons, regex timeout guarding, and precise Excel-compatible aggregate semantics (sum/avg/min/max consume numeric cells only; count is raw row count; exclusions are reported). This is exceptionally detailed behavioral 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?

Dense but never wasteful — every clause earns its place. The structure is logical: operational behavior first, then a 'Semantics:' block for edge cases. For a 15-parameter tool with subtle Excel-compatible behaviors, the length is fully justified rather than bloated.

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 high complexity, zero annotations, and an output schema covering return shape, the description is remarkably complete. It covers purpose, all behaviors, edge cases, and the safety profile ('Read-only'). The only omissions — exact error behavior and the alternative values for the 'values' param — are minor against the depth provided.

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 — and it does thoroughly. It explains location (defaults to true used range), header (first row names columns), where/match (predicate list with all 13 ops), columns (projection), order_by (direction refusal), offset/limit (paging), distinct, aggregate/group_by/records (function list and output shape), and values ('cached' semantics). Only path and sheet are left to inference, a minor gap against 15 parameters.

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?

Opens with a specific, multi-verb statement of scope: 'Filter, project, sort, paginate, and aggregate a range SERVER-SIDE.' The resource ('a range') and the differentiating benefit (reading only needed rows/columns vs. a whole sheet) are explicit, which cleanly separates it from siblings like read_range and get_grid_view.

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 invoke this tool — 'so an agent reads only the rows and columns it needs instead of a whole sheet' — implying it is the choice for server-side subsetting. However, it never explicitly names an alternative tool (e.g., read_range) or states when not to use it, so it stops short of explicit when/when-not guidance.

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