audit_apple_project

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

No annotations exist, so the description carries the full burden. It does disclose the audit checklist (architecture, Tauri v2, safe-area, 44pt, Liquid Glass), which is real behavioral scope. But it never says whether the tool is read-only or writes reports/fixes files, what the findings look like, or how long a full audit takes — gaps that matter for a no-annotation tool.

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?

A single front-loaded sentence led by the verb, with every clause adding a distinct audit dimension rather than filler. Dense but not padded; only the lack of any second sentence on outcome/usage 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?

With zero annotations, no output schema, and 2 optional parameters, the description should say what an agent gets back (findings list, severities, pass/fail) and whether anything is mutated. It covers what is audited but leaves the result contract entirely unspecified.

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 100%, so both 'platforms' and 'project_path' are already documented including the auto-detect default. The description echoes the platform names (macOS, iPadOS, iOS) but adds no new semantics such as path format, symlink handling, or what auto-detect keys off. Baseline 3 is appropriate.

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?

Names a specific verb ('Mengaudit' = audit) plus the resource (Apple project) and enumerates exactly what is checked: architecture, Tauri v2 config, mobile safe-area, 44pt touch ergonomics, and Liquid Glass HIG styling. This scope makes it distinguishable from scaffolding siblings, though it never contrasts itself with the similarly named audit_desktop_project.

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 by the enumerated audit scope — an agent can infer this is a compliance-check tool for Apple-platform projects. There is no explicit statement of when to run it (pre-release? after scaffolding?), no prerequisites, and no pointer to audit_desktop_project for non-Apple targets.

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