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

Adds real context beyond the annotations: async execution, immediate job-id return, background run until status=done, stop_at capping unique places, and the foreign-phone drop default. Annotations already cover readOnly/openWorld/idempotent, so this is a solid addition on top of them.

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 dense sentences, front-loaded with the launch/async fact, then return value, then the two behavioral knobs. No filler, though the parenthetical '(async)' and the restated exclude_foreign_phones default add minor redundancy.

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?

Acknowledges the async model and status=done but never names get_job or get_job_results for retrieving output, which matters since there is no output schema. With 8 parameters at 25% coverage, several inputs remain unexplained for a job-creation tool.

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?

Only 25% of 8 params are schema-documented, and the description explains just two: stop_at (caps unique places, beyond the bare schema) and exclude_foreign_phones (largely restating the schema text). country, scrap_mode, max_per_phone, extra_columns, queries, and zones get no clarification.

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 ('Launch a Google Maps extraction'), which distinguishes it from the enrichment, monitor, and pipeline job siblings. It does not explicitly name those siblings, but the 'Google Maps extraction' scope makes the domain clear.

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?

No when-to-use guidance and no mention of estimate_scrap, the obvious companion tool for sizing a job before launching it. The async/job-id mechanics are stated, but that is behavior, not selection guidance.

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