Run any pac command

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

With no annotations, the description carries the burden of behavioral disclosure. It clearly explains the read-only vs. mutating command distinction, the confirm requirement for changes, and the profile override behavior. It does not mention cwd/timeout handling or return format, but the main safety-relevant behavior is well covered.

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 with no wasted words. The purpose is front-loaded, the read-only vs. confirm distinction is compactly stated, and the profile explanation adds necessary context without bloat.

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 deliberately generic escape-hatch tool, the description covers the essential invocation decisions: what the tool does, how to gate destructive commands, and how to switch profiles. The absence of an output schema is acceptable since the output is pac's own output. The optional cwd and timeoutSeconds parameters are left unexplained, but they are ancillary and named in the schema.

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?

The schema documents args, confirm, and profile, leaving cwd and timeoutSeconds undocumented (60% coverage). The description adds useful meaning for profile—running as another pac auth profile, e.g., tenant admin—and reinforces the confirm behavior, but it does not compensate for the undocumented cwd and timeoutSeconds parameters.

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 clearly states that the tool runs any 'pac <args...>' command directly, and the phrase 'escape hatch' distinguishes it from the many curated pac-specific sibling tools. It lacks a single specific resource because it is deliberately broad, but the verb and scope are unambiguous.

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 gives clear operating context: use this tool to invoke pac directly when a dedicated wrapper is not appropriate. It also provides a concrete decision rule for the confirm parameter—read-only commands run immediately, anything else requires confirm: true. It does not explicitly name alternatives or say 'prefer cs_* when available,' so it misses the top score.

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