Check a plan before acting

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: it 'works without the app' (or against a bundled snapshot) and returns findings plus a playbook to follow — details an agent cannot get from the annotations.

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 and its timing before the exhaustive rule enumeration, which is dense but load-bearing for understanding what is checked. Slight deduction for the very long rule list and a redundant Korean restatement of the opening sentence.

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?

No output schema exists, and the description compensates by saying it returns findings with rule ids and a playbook. Combined with offline-mode disclosure and step-format examples, an agent has what it needs; minor gaps remain around error behavior for unrecognized tool names and whether findings are advisory or blocking.

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 100%, so the baseline is 3. The description goes beyond the schema by spelling out the accepted step formats with a worked example ('add_fire {"hrrpua": 500, "xb": [..]}'), and by tying the boolean flags to concrete rules it checks (user confirmation, fires the user did not ask for).

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 verb and object — 'Review the sequence of tool calls you intend to make BEFORE calling them' — and enumerates the exact checks performed (tool/arg name validation against app or snapshot, BULC rules, HRR from HRRPUA × area, mesh ordering). It is clearly distinguishable from validate_project, sim_preflight and bulc_check_deck, which validate artifacts rather than a planned call sequence.

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 temporal guidance is explicit and front-loaded ('BEFORE calling them'), and the rule list implies the situations it covers (fires, sim runs, meshes, import ordering). It does not, however, state when NOT to use it versus siblings like bulc_check_deck or validate_project, so the agent must infer the boundary.

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