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

Goes well beyond the annotations: it explains determinism ('the same input always gets the same answer'), what the confidence score means, the status taxonomy, the precision taxonomy, that ordering is preserved, that unplaced rows carry a reason, and that overflow rows are not looked up. It also gives concrete coordinate formats accepted. Nothing an agent would be surprised by is left implicit.

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 core action, which is good, but it is a dense wall of long parenthetical sentences. The confidence explanation ('our estimate of how often an answer that sure is right, being refitted against public address records') is verbose and could be one clause; several admin-field lists are repeated twice.

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 full burden of explaining returns, and it does: per-row status, coordinates, precision, confidence with evidence, building classification, admin parts, record_key, map_version, nearest_address for reverse geocoding, and CSV output columns. An agent knows what comes back in every mode.

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%, so the six parameters are already documented in detail, and the description largely restates behavior rather than adding per-parameter meaning. It does add the accepted coordinate formats and the notion that flats/units match to their building, but it does not explain 'background', 'records' vs 'addresses', or 'columns' beyond what the schema says, so baseline 3 is right.

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 opening sentence gives a specific verb, resource, and scope ('Place up to 100 addresses in one call'), and the description also carves out a second capability ('this is also how to turn coordinates into addresses'), which no sibling tool name suggests. An agent can tell exactly what this does without reading 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?

It gives clear usage signals: batch up to 100, coordinates are placed as given, and rows past 100 come back as not looked up, with 'background' triggered automatically past 100 rows. It points at the write_to_sheet sibling for sheet output, but never explicitly says when to prefer find_nearby or get_location_facts instead, so routing is implied rather than stated.

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