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

Annotations declare non-read-only, non-idempotent, open-world, non-destructive, but the description adds behavior they cannot convey: asynchronous job-id return, multi-minute-to-hour duration, and consumption of the user's monthly lead allowance. It explicitly documents the cost-avoidance path via dry_run, which is the key behavioral risk for this tool.

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 sentences, each earning its place: purpose/timing first, prerequisites second, cost warning third. No restatement of the title or filler, and the most decision-relevant facts (async, cost) are front-loaded.

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?

For a 7-param async job-starter with no output schema, the description covers the return shape (job id), the cost model, and the validation path. It does not state how to retrieve results afterward (e.g. mapsdata_get_scrape), which is discoverable from siblings but would close the loop fully.

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 already 86%, so the schema carries most parameter meaning (baseline 3). The description adds real value beyond it by explaining dry_run ('check a request against every rule without spending anything') and the quota consequence of total_limit, which the schema only states indirectly.

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+resource (scrape Google Maps businesses and their emails) and immediately characterizes the operating mode: 'Returns IMMEDIATELY with a job id; the scrape itself takes 5 minutes to several hours.' This is a concrete, distinguishable purpose relative to siblings like mapsdata_get_scrape or mapsdata_cancel_scrape.

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?

Gives explicit prerequisites ('confirm the category with mapsdata_search_categories and the region with mapsdata_list_regions') and names the sibling tools to call first, plus the rationale that these are the majority of rejections. It also names a when-to-use variant (dry_run) with its purpose. Nothing is left to inference.

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