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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds the crucial undisclosed fact that this operation spends subscription credits, capped by max_results, and that execution is asynchronous with a job_id to poll. That cost-and-async disclosure is exactly the kind of context annotations cannot convey; it stops short of saying whether unused credits are refunded or how long the job lives.

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 short sentences, each carrying a distinct load: what it does, what it costs, and how to follow up. The most dangerous fact (credit spend) and the most common mistake (re-searching instead of polling) are both 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 an async, credit-spending tool with no output schema, the description covers the job_id and the polling rule but omits what else the response contains, whether the job can be cancelled via cancel_search_job, and how results are eventually retrieved or saved. Combined with the undocumented filters object, an agent can call this correctly but not fully exploit it.

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 only 33%, and the description compensates only for max_results, recasting it as a spending cap rather than a plain result limit. The large nested 'filters' object, which holds roughly twenty undocumented fields such as industries, employee_size, and location arrays, gets no explanation at all in either schema or description.

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 description gives a specific verb and resource ('Start an asynchronous paid search') plus the defining traits: it is async, it is paid, and it returns a job_id. That immediately separates it from synchronous siblings like preview_leads and from the polling siblings get_search_job and get_search_results.

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 states the use case (kick off a search) and gives an explicit negative rule: 'NEVER start another search to poll', which routes the agent to the polling tools. It does not name get_search_job or get_search_results explicitly, nor does it distinguish this from preview_leads, so the routing is implied rather than enumerated.

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