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

Annotations already establish readOnly/openWorld/non-destructive, and the description adds a genuinely useful behavioral caveat that annotations cannot convey: "Suggestions come from autocomplete and are not validated addresses." That tells the agent results may be wrong or incomplete and likely need a follow-up confirmation step. It stops short of describing result volume, ranking, or how locationBias affects outcomes beyond what the schema says.

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?

Purpose is front-loaded in the opening sentence, followed by usage context and then exclusions — a sensible order. The middle sentence is long and could be split, but every clause carries information about trigger conditions or accepted input formats, so little is wasted.

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 an output schema present, the description needn't explain return values, and it covers purpose, triggers, input forms, a quality caveat, and exclusions. What remains thin is how multiple addresses should be handled given the "one address" phrasing versus the spreadsheet mention, which is the main ambiguity for a tool resolving lists of stops.

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 50%: locationBias is well documented inline, but query has no schema description. The phrase "for one address or place name" partially compensates by implying query is a single free-text name rather than a batch, though this sits in slight tension with the mention of pasted spreadsheets. Baseline 3 is appropriate since the schema carries most of the parameter meaning.

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 first sentence gives a specific verb and resource ("Finds Google address suggestions, with place IDs") and scopes the input to "one address or place name," so the agent knows exactly what comes back. It distinguishes the tool from unrelated capabilities in the negative clause, but never names a sibling (e.g., select_addresses) as the adjacent option, so it falls short of a full 5.

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 states concrete triggering contexts — planning deliveries, ordering driving stops, optimizing multi-stop routes — and explicitly lists input forms (spreadsheets, CSV, numbered lists), plus clear exclusions (place recommendations, package tracking, transit directions). What's missing is routing to an alternative tool when the exclusion applies, so there is when/when-not but no named alternatives.

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