safari_tabs

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: the 50-tab bound and the Automation-permission requirement for Safari, both of which an agent needs before invoking.

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 short clauses with zero waste; the core action and output shape are front-loaded, with the bound and permission noted after. Every sentence 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?

With an output schema present, return values needn't be explained further, and the zero-param schema requires no input documentation. Combined with annotations covering safety, the description's additions (bound, auth requirement, sibling routing) make it complete for an agent to call correctly.

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?

There are zero input parameters, so the baseline is 4. The description correctly adds no parameter detail and instead documents the output shape (url + title) and result cap, which is appropriate for a no-arg tool.

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 (list) and resource (open Safari tabs), plus the output shape (url + title pointers) and a bound (50). It also distinguishes itself from the sibling safari_open by directing URL-opening there, so an agent can tell the two apart without opening either 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?

The line 'See safari_open to open a URL' explicitly names the alternative and the condition that selects it, which is clear routing. There is no further elaboration on exclusions (e.g. tab content vs. pointers), so it stops just short of a full when/when-not treatment.

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