tally_read_exported_table

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 does so thoroughly: it discloses read-only semantics, behavior when TallyPrime is closed, pagination behavior, the meaning of totalRows relative to the file, the fact that values are text, and the safety warning that text fields are data rather than instructions. This is unusually complete 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?

The description is long but every section earns its place: WHEN TO USE, RETURNS, PAGINATION, DOES NOT RETURN, and the safety warning are all distinct and load-bearing. It is front-loaded with the core purpose and structured so an agent can quickly extract invocation steps, return semantics, and caveats.

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 there is no output schema and no annotations, the description provides everything an agent needs: how to trigger the catalogue, how to request a specific table, what to expect in the response, how pagination works, how to interpret totalRows, and a critical safety warning. No material gap remains for correct invocation and interpretation.

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?

The input schema already documents all four parameters at 100% coverage, so the baseline is 3. The description adds workflow-level context around `table` (catalogue vs. named table) and confirms defaults, but it does not add significant semantic meaning beyond what the schema already states. The extra insight about `totalRows` is useful but concerns output behavior rather than parameter meaning.

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 states a specific action ('Read one table'), a clear resource ('out of a company exported spreadsheet'), and a precise workflow: call with no table for the catalogue, then name the desired table. This differentiates it from siblings like tally_get_vouchers or tally_get_statement, which operate on computed or live data rather than raw exported files.

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 explicitly says when to use the tool ('after tally_list_exported_books has told you which companies exist'), gives the intended call sequence ('Call it once with no `table`... then again naming the one you want'), and states what it does not return ('live figures'). This gives an agent clear rules for invocation and for choosing not to use it.

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