rupa_periksa

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

Annotations already indicate destructiveHint=truehare, so the description correctly implies mutability (issuing certificates). It adds behavioral context beyond annotations: it explains the weighted rules (wajib vs peringatan) and the critical behavior that missing measurements are counted as FAILED, warning against silent non-execution. This is valuable context that helps the agent understand the tool's semantics, even though it does not detail all destructive side effects (e.g., whether copying files is considered destructive).

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 a single paragraph that packs critical information without fluff. It front-loads the core purpose (evaluate and issue certificate), then explains the distinctive output and rule semantics. Every sentence adds value: purpose, differentiation, rule behavior, and the caution about missing measurements. It is appropriately sized for the tool's complexity.

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 the tool's moderate complexity (5 parameters, no output schema) and the rich annotations (destructiveHint), the description covers the most important aspects: what the tool does, how to choose between direct GLB and scene, and how rules behave. It lacks explicit information on return values or how the certificate is structured, but since there is no output schema, the description could have mentioned the output format. However, it is sufficient for an agent to invoke the tool correctly.

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 covers 100% of parameters with descriptions, so baseline is 3. The description adds context by explaining the semantics of 'berkas' vs 'ruang' (direct GLB vs scene), which is already in the schema but re-emphasized. It does not add new parameter meaning beyond the schema, such as exact formats or examples of the 'spek' parameter's contents beyond the built-in paths. Thus, it does not exceed baseline significantly.

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 clearly states that the tool evaluates a scene against a specification (SPEK) and issues a certificate. It goes beyond a simple verb+resource by explaining the distinctive output (a list of promises with numbers that prove or refute them), which distinguishes it from sibling tools like rupa_ukur (measure) or rupa_lihat (view). The mention of the certificate attached to the file adds specificity.

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 explicitly explains when to use direct GLB measurement via 'berkas' vs. the scene in 'ruang' when Blender is needed: 'Ini yang seharusnya dipakai untuk aset yang sudah jadi... Kosongkan untuk mengukur ADEGAN di `ruang` (butuh Blender).' It also clarifies the 'tempel_ke' behavior (copy the file and attach certificate, never overwrite the source). This gives clear guidance for selecting the appropriate mode, although it does not explicitly compare to sibling tools, it provides enough context for usage.

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