system_open_app

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

Annotations already declare the safety profile (readOnly=false, destructive=false, idempotent=true, openWorld=true). The description adds two traits not covered there: the permission requirement ("permissions: none") and the hard scope restriction against launching arbitrary binaries. It does not, however, mention the human-approval path implied by the _approvalId parameter.

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 carrying the action, the scope limit, and the version/permission metadata in brackets. No filler, nothing that could be cut without losing information.

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?

An output schema exists, so return values need no explanation, and the parameters are fully documented in the schema. The remaining gap is the approval workflow (when _approvalId must be supplied) and routing among the open/activate/run siblings, which the description leaves implicit.

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 schema already documents all three parameters, including the idempotency and approval keys. The description's "exact bundle ID" wording adds only a mild nuance about matching semantics, so the baseline of 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?

Specific verb + resource ("Open an installed app by exact bundle ID") with an explicit scope boundary ("does not execute arbitrary binaries"). That boundary cleanly separates it from siblings like system_run_command, system_open_url, and system_activate_app without the agent needing to open any 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 exclusion of arbitrary binary execution implies the right alternative (system_run_command), but no sibling is named and no when-to-use condition is stated for choosing between this, system_activate_app, and system_open_url. Usage is only implied.

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