find_hard_coded_inputs

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

No annotations are provided, so the description carries the full burden. It discloses that the tool uses heuristic discovery and specifies the criteria (plain number referenced by at least one formula). However, it does not mention behavior aspects such as whether it is read-only, performance implications, or what happens if called multiple times. The description provides basic transparency but lacks depth.

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 a single, concise sentence that front-loads the key action ('Heuristic discovery'). It avoids unnecessary words and clearly conveys the purpose. While it is efficient, it could benefit from slight structuring (e.g., separate bullet for criteria) without increasing length.

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 the tool's moderate complexity and the presence of an output schema (not shown but mentioned in context), the description adequately explains the purpose and criteria. However, it lacks information on the output format (likely cell references) and does not address prerequisites (e.g., workbook must be open). With no annotations, completeness is acceptable but could be improved.

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 schema has 0% description coverage for the single parameter 'workbook_name'. The description does not mention the parameter at all, leaving its semantics (e.g., how to specify the workbook) unexplained. With minimal schema coverage, the description should compensate by clarifying the parameter, but it fails to do so.

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's purpose: heuristic discovery of deterministic numeric inputs (plain numbers referenced by formulas) that are candidates for replacement. It uses specific language ('discovery', 'candidates for replacing') and distinguishes from sibling tools like 'discover_inputs' and 'propose_distributions_for_inputs' by focusing on hard-coded cells.

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 implies usage context (preliminary step for replacing constants with distributions) but does not explicitly state when to use or not use this tool versus alternatives like 'propose_distributions_for_inputs' or 'discover_inputs'. No examples of appropriate scenarios are given.

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