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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description goes further by stating 'writes no files and uses no network' and 'read-only generated output.' It also discloses that output is structured file-by-file for an Xcode agent to write. This adds meaningful behavior beyond the annotations, though the idempotentHint is not explicitly reinforced.

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 well-structured with clear sections: main action, return value, usage, inputs, and effects. Each sentence provides distinct information, and the most critical fact (what the tool does) is front-loaded. Minor redundancy in 'read-only generated output' and 'writes no files' could be trimmed, but overall it is efficient.

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 tool with 11 parameters, nested objects, and an output schema, the description offers a good high-level context: it clarifies the use case, output structure, and side-effect profile. The only notable gap is the misleading 'kind' reference and the lack of explicit mention of the output schema (though the schema itself is present). Given the schema's richness, the description suffices for guiding invocation.

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%, so the baseline is 3. The description adds a helpful note that 'description' is the feature brief and that 'platform' constrains the package. However, it also mentions 'kind' as an input, yet no parameter named 'kind' exists in the schema—this is misleading. The ambiguity undermines the added value and could lead an agent to look for a non-existent parameter.

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 opens with a specific verb+noun: 'Generate a scaffolded Apple-native feature package from a description.' It then enumerates the output file types, making the tool's purpose unmistakable. The 'Use' clause also distinguishes it from repair tools, and the name 'feature' aligns with new-surface generation.

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 states when to use it ('for new Apple-native surfaces') and when not to ('not for repairing existing app bugs'). However, it does not name a specific alternative tool (e.g., axint.repair or axint.scaffold), so the guidance is clear but lacks a direct pointer to the sibling.

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