Apple Suggest Shortcuts

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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering the safety profile, so the bar for the description is lower. It adds mild behavioral context by framing results as derived from 'current Apple data surfaces' (live/computed, not static) and by positioning the tool as a completion fallback. It does not address behavior for empty queries, ranking, or no-suggestion cases, but with annotations present this is an acceptable contribution.

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 totaling roughly 24 words, with the action front-loaded in the first sentence and the usage context in the second. No fluff, no repetition of the title, no filler—every clause earns its place.

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?

The output schema covers return values, annotations cover the safety profile, and the description covers purpose plus a usage trigger—adequate for a simple 2-optional-parameter, read-only tool. The clear remaining gap is the parameter contract: an agent must guess what query and limit mean. It is viable but leaves meaningful information to inference.

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 0% and the description adds no direct meaning for either parameter: 'limit' (an oddly typed integer-or-string with default 25) and 'query' (nullable string) are never explained. The 'completion fallback' framing weakly implies query is a completion prefix and limit caps results, but that is inference, not documentation. With zero schema coverage, the description was obligated to compensate and largely did not.

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 states a specific action, 'Suggest Shortcuts', clearly identifying verb and resource. The completion-fallback note gives it a distinct role, and 'using the current Apple data surfaces' signals live system context. However, 'current Apple data surfaces' is vague jargon, and it does not explicitly differentiate from siblings like shortcuts_list_shortcuts or apple_list_shortcuts_for_capability.

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 second sentence is an explicit trigger condition: 'This is a completion fallback for clients without MCP completion support,' telling the agent precisely when this tool is the right choice. It falls short of a 5 because it names no alternatives and gives no when-not-to-use guidance, despite a large apple_suggest_* sibling family where such routing would help.

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