Sim start

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

Annotations declare a non-readonly, non-destructive, non-idempotent write, and the description adds substantial behavior on top: refusal while another run is active, hard refusal on preflight errors, deck emission path (.bulc → .fds next to the saved project, or Documents/bulc_<folder>/ for unsaved projects), run duration (GPU minutes to hours), and checkpoint resume semantics for restart=true.

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 the hard confirm requirement, and the dense middle sentence packs real constraints (preflight refusal, force, deck paths, active-run refusal) without filler. Slight redundancy: the [bulc-mcp] lines restate the preflight / user-go-ahead requirement already made in the first sentence, and the rules reference is metadata rather than guidance.

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 7-parameter, irreversible, long-running action with no output schema, the description covers prerequisites, gating conditions, side effects (deck file written to disk), expected duration, and the follow-up polling step. Nothing needed to invoke it safely is missing.

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 86%, so most parameters are already documented, but the description still adds meaning: solver's default (gpu) which the schema enum does not state, restart=true as checkpoint resume, force tied to explicit user acceptance, and location's default tied to whether the project is saved. Only cpu_threads/folder_name get no extra narrative, and those are covered in the schema.

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?

Specific verb + resource ("Start the fire simulation in the running app") with the live-app scope stated, which separates it from the headless/other run siblings and from the sim_stop / sim_status / evac_run family. An agent can tell what this does and what it is not without opening the 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?

Explicit preconditions and sequencing: sim_preflight runs first, the tool refuses on preflight errors unless force=true and the user has explicitly accepted, confirm=true is required because the user must have agreed, and the agent should poll sim_status afterwards; "Live app only" excludes a whole context. No guidance on when to prefer it over the similarly-named run_simulation sibling, which is the one remaining gap.

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