connect_card

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

No annotations exist, so the description must fully disclose behavior. It states side effects ('opens a serial session; does not export private key material') and limitations ('pilot-only'), but missing details like error conditions, resource cleanup, or thread safety. The disclosure is adequate but not comprehensive.

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 sentences, no redundancy. The key action and side effects are front-loaded. Minor deduction for the 'Preview:' prefix, which is meta rather than descriptive.

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 not be explained, but the description does not reference the output schema or clarify what 'reports availability' means structurally. Given the complexity of USB transport and hardware interaction, some guidance on expected output handling would improve completeness.

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 100% with descriptive field descriptions. The tool description adds no extra parameter context (e.g., no mention of pin sensitivity or timeout implications). Baseline 3 is appropriate as the schema already does the heavy lifting.

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 it 'connects to an AP2 Vault Card / SE050 hardware signing bridge' and 'pings the USB CDC transport and reports availability', which distinguishes it from sibling tools like sign_action and list_envelopes. However, the purpose could be more precise about the exact action (e.g., 'initialize hardware connection') rather than starting with 'Preview'.

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 mentions 'pilot-only' and 'emulated mode is the default', implying limited contexts, but it does not explicitly state when to use this tool versus alternatives (e.g., 'use before sign_action' or 'only for hardware signing setup'). No guidance on prerequisites or exclusions is provided.

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