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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuinely new context: it is a pure string builder, the output is a vCard 3.0 / RFC 2426 document, and the payload can grow long enough to affect QR error-correction choice — a non-obvious sizing behavior.

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, both front-loaded: what it builds first, then the hand-off and the sizing tip. No boilerplate, no restatement of the title, every clause is actionable.

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 14-parameter, zero-required builder with no output schema, the description covers what matters: the emitted format and how to consume the return value. The one gap is that it never notes all fields are optional or what a minimal useful card requires, which matters given zero required parameters.

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% with all 14 optional fields documented (firstName, lastName, phone, workPhone, address parts, etc.), so the schema carries parameter meaning completely. The description adds no field-level guidance such as which fields are needed for a usable card — baseline 3 applies.

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 and output artifact: 'Build a vCard 3.0 contact payload (RFC 2426)'. The contact/vCard framing immediately distinguishes it from the sibling payload builders (qr_payload_email, qr_payload_geo, qr_payload_sms, qr_payload_wifi) without needing 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?

Gives an explicit downstream step — 'Pass the result as `data` to generate_qr_code' — which is exactly the chaining an agent needs, plus a practical tip to use error correction L or M for long cards. It stops short of naming when to prefer this over the sibling payload types, but the purpose line makes that self-evident.

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