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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuine behavioral context beyond that: the 10-result cap and the important caveat that suggestions are candidates, not guaranteed deliverable, which changes how an agent should treat the output.

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?

Front-loaded with the purpose, then the output contract, then the verification caveat, then an example. The inline example partially duplicates the schema's 'examples' block, which is slight redundancy, but the prose sentences themselves all earn their place.

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 carries the burden of describing returns and does so (count and reliability caveat). Adding the verification path closes the main gap; only finer details like pagination or rate limits are absent, which is minor for a read-only autocomplete.

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 address_prefix, city, state, zip_code and _apiKey; the baseline is 3. The description restates the same optional filters and shows a usage example, but adds no format guidance (e.g. ZIP vs ZIP+4, state casing) beyond the schema.

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 resource ('Autocomplete a partial US address') and defines the output shape ('up to 10 full address suggestions'). It also names the sibling it complements (lob_verify_address), so an agent can distinguish it from the verification tools without opening a 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?

Clearly frames the tool as a candidate generator and explicitly routes validation to lob_verify_address, which is the key decision an agent must make between this and its sibling. It stops short of stating an explicit 'do not use when' condition, but the input precondition (partial primary line) is implied by 'partial'/'prefix'.

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