presolve_check

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

With no annotations, the description carries the full burden and does well: explicitly read-only ('nothing is deleted or started'), discloses the overwriteable-files risk (names only, no deletion), and honestly flags the memory heuristic as uncertain by roughly 3x. It doesn't cover permissions or how verdict thresholds are derived, keeping it from a 5.

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?

Purpose is front-loaded and every clause carries information, but the long parenthetical on the memory heuristic and the trailing args summary make it denser than ideal. Structure is functional rather than crisp.

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 an output schema exists, the description still usefully explains `verdict` (ok/warn/stop) and `reasons`, and covers all preflight checks an agent needs. It is essentially complete, with only minor gaps like exact verdict thresholds.

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%, yet the description meaningfully explains all four: ncpu (0 = not given), memory ('words as for the solver, e.g. 200m'), and working_dir ('the newest .k in it is used') with deck_path as the alternative source. deck_path's own resolution semantics are left slightly implicit, so not quite a 5.

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 specific verb and resource ('Check before a solve') and enumerates exactly what it reports: free RAM/disk, memory estimate, overwriteable result files, ncpu vs cores, and audit_deck findings. This is clearly distinguishable from siblings like audit_deck or solve_analysis, which do subsets of this.

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?

'Check before a solve' gives clear timing context, and the description notes it folds in audit_deck results, implying it supersedes a separate audit call in this flow. It does not explicitly name alternatives or exclusions (e.g. vs check_run_health or audit_deck alone), so it falls short of a 5.

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