bw_run_remodeling

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

With no annotations, the description fully carries the safety burden. It clearly warns that this is a WRITE OPERATION WITH DATA IMPACT, that data is restructured/converted, and that it cannot simply be undone. It also explains that the call is asynchronous, which prevents the agent from wrongly expecting immediate completion.

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 front-loaded with the most critical information, the destructive/asynchronous nature, before defining the actions. Each sentence contributes distinct information with no filler or repetition.

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 complex write operation with no output schema, the description covers the essential points: what the actions are, why the operation is dangerous, and how to check completion. It is complete enough for an agent to invoke the tool correctly and safely.

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 already has 100% description coverage, so the baseline is 3. The description adds real value by explaining what each action value does: execute starts, restart resumes, reset resets whole, reset_step resets the current step. This goes beyond what the schema alone provides.

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 uses a specific verb and resource: 'Start, restart or reset a remodeling request', and it goes beyond the name by enumerating the four actions. It immediately signals that this is not read-only, distinguishing it from monitoring tools like bw_get_remodeling_request.

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 gives clear context on when to invoke it — for a new request, a failed one, or to reset whole/current step — and tells the agent to monitor completion via bw_get_remodeling_request. It does not explicitly spell out 'do not use this for plain reloads' but it says 'not a plain reload', which effectively excludes that alternative.

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