Add an HTTP(S) URL, with optional title and preview, to Safari Reading List. Use it to save web pages for later reading, optionally syncing through iCloud.
Add an HTTP(S) URL, optional title, and preview to Safari Reading List; may sync through iCloud.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| title | No | ||
| preview | No |
Changes observed during successful MCP inspections.
v3.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the mutation profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the bar is lower. The description adds value beyond them by disclosing the iCloud sync side effect and constraining input to HTTP(S) URLs, which is real operational context not present in the schema.
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 with no wasted words; the core action comes first and the side-effect caveat trails after.
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 simple three-parameter mutation with no output schema and safety hints already covered by annotations, the definition is nearly sufficient. The remaining gap is duplicate handling and any prerequisites (e.g. Safari running), which are not addressed.
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 0%, so the description has to carry the parameter burden. It does flag that title and preview are optional and that the URL must be HTTP(S) (the schema's format:uri alone does not enforce that), but it never explains what 'preview' actually is, leaving one of three parameters semantically opaque.
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 (add) and resource (Safari Reading List) plus the exact payload (URL, optional title, preview). This is plainly distinct from the other Safari siblings (open_tab, navigate_tab, list_tabs), so an agent can route to it without opening the 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?
Usage is only implied: the wording makes clear this is for saving a page for later, but it never states when to prefer this over apple_safari_open_tab or what happens if the URL is already on the list. No exclusions or alternatives are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.