write_and_audit_deck

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

No annotations are provided, so the description carries the full burden, and it does substantial work: it discloses the write side effect and target location, the output_name default and .k constraint, and the important guarantee that 'an existing file is never replaced'. It also explains safe_to_solve semantics (false on error-severity findings or missing reference cards) — though it doesn't say how a failure in the write step itself surfaces or whether a partially written file is left behind.

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?

Front-loaded with the action chain (write → audit → compare), then side-effect placement, then args. It is dense and the safe_to_solve sentence is a long nested parenthetical, but essentially every clause carries information an agent needs.

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?

For a composite mutation tool with no annotations, the description covers placement, naming, overwrite policy, the safe_to_solve gate, and points the agent at `reasons` and `diff`. An output schema exists so return shapes needn't be explained. The main gap is the unexplained analysis_index and error-path behavior.

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 0%, so the description must compensate: it explains reference_path ('the standalone deck to compare with') and output_name ('a plain .k name; default wb_written_<time>.k') well. However, analysis_index is only listed by name in the Args line with no meaning, indexing base, or default given, leaving one of three parameters undocumented anywhere.

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?

States a precise compound action — write the deck via the same Analysis.WriteInputFile path as write_solver_input (explicitly 'no solve'), then audit via audit_deck and optionally compare via compare_decks. This differentiates it cleanly from write_solver_input, solve_analysis, audit_deck and compare_decks without opening any schema.

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?

Clear context for when the comparison half runs: 'with reference_path, compare it with the reference deck', implying reference_path is optional and changes behavior. It does not explicitly say when to prefer this over calling write_solver_input + audit_deck separately, so no exclusions are stated.

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