figcraft_audit_layout

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

With no annotations supplied, the description carries the full burden. 'Audit' and 'Menghasilkan skor kualitas dan payload bukti' strongly imply a non-mutating read, but this is never stated outright, and the description does not say what scope is examined (current open document, selection, or page) or whether it requires an open file. The scoring output behavior is disclosed, which is genuinely useful context.

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 tightly packed sentences: the first front-loads the audit scope and enumerated checks, the second states the output. No filler, though the enumerated list is dense enough that an English-language agent may need a moment to parse it, and the description is written in Indonesian while the surrounding tool ecosystem is English-named.

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?

Since there is no output schema, the description must explain return values and does so partially (quality score plus evidence payload). However, for a zero-param tool whose behavior depends entirely on ambient state, the omission of what document/scope is audited and whether a file must be open leaves a real operational gap.

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 with 100% schema coverage, so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly avoids restating schema details that do not exist.

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 names a specific verb ('Audit kualitas layout... secara otomatis') and enumerates the exact checks performed: overflow, raw escaped \n, flat layer hierarchy without Auto-Layout, and responsive artboard completeness. This is far more informative than a restatement of the name, though it never explicitly contrasts itself with the sibling fix_overflow, which is the natural confusion point (audit vs. remediate).

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?

Usage is only implied: the mention of 'Harness MCP quality checkpoints' hints that this is a pre-check step, but there is no explicit statement of when to call it versus fix_overflow or inspect_document, and no precondition such as requiring a file to be open. The agent must infer the workflow position from the output description alone.

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