audit_layout

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

With no annotations, the description carries the full behavioral burden. It does disclose a meaningful behavior — that the tool returns a quality score plus an evidence payload — which is valuable since there is no output schema. However, it never states that the operation is read-only/non-mutating, whether it inspects the whole document or a selection, or what happens on an empty canvas.

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?

Two sentences with no filler: the first front-loads purpose and the enumerated check list, the second front-loads the return contract. The check list is long but each item is a distinct detection rule, so it earns its space. Slightly dense enumeration keeps it from a 5.

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 zero-parameter, self-contained diagnostic, the description covers both what is checked and what comes back (score + evidence payload), which is more than the structured fields provide since there is no output schema. It leaves out the score scale/thresholds and whether results are persisted, but nothing essential to invoking it is missing.

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 tool takes zero parameters, so there are no parameter semantics to explain; the baseline for a parameterless tool applies. The description correctly describes the tool as a whole-canvas audit rather than implying any scoping input.

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 ('Audit') and resource ('kualitas layout kanvas') and enumerates four concrete checks: overflow text, raw escaped \n, flat layer hierarchy without Auto-Layout, and responsive artboard completeness. An agent can tell this is a diagnostic tool, not a fixer. However, it never names a sibling such as figcraft_fix_overflow or figcraft_create_responsive_system, so the differentiation from those is only implicit.

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?

Mentions it produces evidence payloads 'untuk Harness MCP quality checkpoints', which implies the workflow where it belongs. But there is no explicit when-to-use or when-not-to-use guidance, and nothing tells the agent to run this audit before calling fix_overflow or create_responsive_system rather than after.

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