rupa_adegan_terbit

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

Annotations already declare destructiveHint=true, and the description strongly complements this with rich behavioral detail: base64 embedding, the blank-screen failure mode under strict CSP, the 16 MB budget checked before writing, and the 4/3 byte inflation cost. This goes well beyond the annotation signal and gives an agent genuine expectations about side effects and failure behavior. No contradiction with 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?

The description is longer than minimal, but every sentence is dense with operational value: output format, embedding strategy, failure mode, cost math, and mode semantics. It is front-loaded with the core purpose before the caveats. Could be slightly trimmed, but no sentence is wasted 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?

With no output schema and a destructive hint, the description covers the tool's behavior thoroughly: output format, embedding, budget enforcement, and mode differences. The only gap is that it never states what the tool returns (success status, path, or error structure), which would help an agent interpret the call result. This is a minor omission for a write-and-return 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 50% (berkas and ruang have descriptions; judul and mandiri do not). The description directly compensates for the undocumented mandiri parameter by explaining what each boolean value produces. The base64 and budget details add meaning to the output context. judul remains undocumented in both places, but it is self-evident enough that this is a minor gap, not a failure to compensate.

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 states a specific verb+resource+output: publishing the scene (adegan) as a self-contained HTML page with orbit, click-select, and per-object numbers. It clearly differentiates the deliverable (a standalone HTML document with embedded assets) from sibling tools like rupa_ekspor and rupa_adegan_lihat by describing the exact output format, leaving no ambiguity about what this tool produces.

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 explicit usage context for the two mandiri modes: mandiri=true for static servers producing a complete document, and mandiri=false for publishers with their own skeleton producing an HTML fragment. However, it does not name sibling alternatives or state when to prefer this tool over rupa_ekspor or other scene tools, so the guidance is clear for mode selection but lacks explicit exclusions.

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