audit_interface

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

Annotations only declare readOnlyHint=true; the description adds the material behavior beyond that — the operation is a remote API call requiring a key, and there is a documented offline fallback. It does not cover failure modes such as an invalid key or rate limits, so it stops just short of a 5.

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?

Three sentences: capability and return contents first, then the auth requirement, then the fallback. No filler, and the result enumeration earns its length because there is no output schema.

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, the description carries the return-value burden and does so (findings, severity, remediation, impact, score, type, strengths, top three fixes). Together with the auth prerequisite and fallback, an agent has everything needed to decide whether and how to call it.

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 100% and all four parameters (depth, locale, context, description) are documented in the schema itself, including enum meanings and the 20–5000 character range. The description adds nothing about parameters, so this sits at the baseline for schema-covered inputs.

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 and resource ("Audit a described screen or flow") and then enumerates the deliverable: findings mapped to principles and UX smells with severity, remediation, business impact, a score, detected interface type, strengths and three priority fixes. This is precise enough to separate it from list_smells or get_smell without opening a 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?

Gives an explicit gating condition ("Pro mode only (UXUI_API_KEY set)") and a named alternative path when that condition fails: use detect_smell then suggest_fix, which run offline. Both the when and the when-not are stated with the sibling tools to use instead.

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