Read an Excel table

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

Beyond the annotations (readOnly, idempotent, non-destructive, open-world), the description discloses the two-step discovery-then-read flow, the exact row shape including excel row numbers, that empty rows are removed, the 25 MB refusal limit, and that `cols` appears in the answer. That is a rich behavioural picture that the annotations alone would not convey.

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 first sentence states what it does and the scope; the second paragraph walks the call sequence in order. No filler, and the discovery-first instruction is front-loaded where an agent will read it.

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 8 parameters and no output schema, the description still explains the return shape (arrays starting with the excel row number) and the `cols` field, plus the size ceiling. An agent has everything needed to make a correct first and second call.

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 already 100%, so the baseline is 3, but the description adds real meaning: `find` matches any cell text such as a province or group name, `offset` is for paging, and `col_offset` matters because newest values in wide monthly series sit at the right end. It does not explain `max_rows`/`max_cols` interplay beyond what the schema says.

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?

"Read an Excel table of a statistical release as compact rows" gives a concrete verb and resource, and the parenthetical "works for any release with an xlsx/xls file" signals it is the generic reader. It stops short of naming the specialized siblings (am_gdp, am_inflation, am_labour_force) that could serve the same data, so an agent must infer the division of labour.

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?

Strong procedural guidance: call first with only `id` to get the sheet list, then pass `sheet`; use `find` for a province or group, `offset` to page, `col_offset` for wide monthly series, and files over 25 MB are refused. The only gap is that it never says when to prefer this generic reader over the topic-specific sibling tools.

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