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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's added value is the non-obvious disclaimer that parsing performs no address validation. That is a real behavioral trait an agent would otherwise assume wrongly. Minor gap: it doesn't say whether malformed or ambiguous input errors out or returns partial fields.

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, zero filler: what it returns, where the input comes from, and what it does not do. The scope caveat is front-loaded before the agent could form a wrong assumption.

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 no output schema, the description correctly compensates by enumerating the returned fields, and it clarifies the single parameter's expected shape. What's missing is failure behavior for unparseable input, which matters for a parser but is a modest gap given the otherwise complete picture.

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% and the schema already states format, min/max length and newline/comma separation. The description adds the origin example ('a line copied from an email or an order'), which is mild contextual reinforcement rather than new semantics, so 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?

Specific verb ('splits') plus resource ('a pasted address') plus the exact output fields it produces (name, street, city, state, ZIP, country). It also names create_shipment as the consumer, so it is clearly distinguishable from the shipment-creation siblings.

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?

It establishes the workflow context ('free text ... becomes the fields create_shipment takes') and explicitly bounds its own scope: 'It only parses; the address is checked when the shipment is created.' This tells the agent not to rely on it for validation, though it stops short of naming an alternative validation tool.

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