fill_opening

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: it enumerates the destructive steps (removes reveal faces, refills wall faces copying material/orientation, closes the bottom for a from_floor opening, erases seams), states the refusal condition, and discloses undo grouping ('One undo step'). It omits nothing major except any mention of what dry_run or group actually do.

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?

Single dense paragraph that front-loads the primary action before the mechanics, preconditions, and units. It is long but nearly every clause adds a distinct behavioral fact, with minimal filler.

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 mutation tool with no annotations and no output schema, the description supplies the safety-relevant behavior (destructive steps, refusal, single undo step) that an agent needs to call it safely. The remaining gap is that several input parameters, notably dry_run and group, are left entirely undefined.

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 description coverage is 0% across 8 parameters, so the description must compensate. It clarifies units ('metres') and defers the rectangle args to cut_opening, and from_floor/wall_faces are inferable from the prose, but dry_run, group, and axis are never explained anywhere.

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+resource ('Fill a rectangular opening back in') and immediately lists the concrete effects, which cleanly distinguishes it as the inverse of the sibling cut_opening (explicitly named). An agent can identify it 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?

It anchors usage to the sibling ('Takes the same rectangle arguments as cut_opening') and gives an explicit refusal precondition ('Refuses if both wall faces are already solid there'). It does not spell out when-not to use it beyond that refusal, so it stops short of full alternative routing.

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