discover_inputs

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

No annotations provided, so description carries the burden. It discloses ranking behavior based on reference count and magnitude, and identifies the output as a list of candidate cells. It does not describe side effects, destructive actions, or output structure beyond ranking, leaving some gaps.

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?

Two sentences, no fluff: first describes the tool's function and ranking methodology, second provides a clear usage suggestion. Every sentence earns its place.

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?

There is an output schema (not shown), so return values are covered. The description explains the ranking criteria and suggests a pairing, but omits prerequisites (e.g., workbook must be open) and edge cases. Parameter semantics are absent, lowering completeness.

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%. The description mentions neither workbook_name nor limit, nor does it explain that limit controls the number of candidates. It adds no meaning beyond the schema titles, failing to compensate for the lack of parameter descriptions.

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 clearly states the tool discovers candidate input cells (numeric cells referenced by formulas) and ranks them by likelihood of being uncertain inputs, using reference count and number magnitude. It also distinguishes itself from the sibling propose_distributions_for_inputs by suggesting pairing, indicating a sequential relationship.

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 explicitly advises to pair with propose_distributions_for_inputs, providing a usage sequence. However, it does not specify when not to use this tool or contrast it with alternatives like find_hard_coded_inputs, missing full exclusion guidance.

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