remove_scaffold

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

With no annotations, the description carries the full burden and does so: it discloses the destructive scope (only scaffolder-generated services), the mutation of project.py imports, the failure mode of the naive approach, the refusal condition for hand-written services indicated by the missing generated marker, and the post-condition that the server must be restarted.

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?

Three tight sentences front-load the action and the undo rationale before the caveats, and the Args block is minimal. No sentence is filler; each conveys a distinct constraint or consequence.

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, return values need not be explained, and the description still notes that refusals are reported. Safety, side effects, refusal conditions, and required follow-up are all covered for a single-parameter destructive tool.

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, and it does: 'Service name slug, the directory name under server/transforms/' tells the agent the exact format (slug) and the filesystem location the value must match, which the bare schema type 'string' does not.

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?

Opens with a specific verb+resource ('Delete a scaffolded service directory and its imports in project.py') and names the exact artifact affected. It is clearly distinguished from the sibling scaffold_transform (create) and from list/get transforms.

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?

Explicitly states when to use it ('Use this to undo a scaffold') and contrasts it with the tempting alternative (deleting the directory by hand), explaining that manual deletion leaves imports behind and breaks server startup. It also names the required follow-up action (restart the server).

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